Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    themes related to personal conflict and emotional reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "in" followed by a determiner

    np_acts-logits-general · gemini-2.0-flash

    prepositions like in, through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SwitchCompat
    -0.60
    neros
    -0.56
    züglich
    -0.55
    Географиясе
    -0.55
     Hatfield
    -0.54
     بلکه
    -0.54
     fixé
    -0.53
     Futuro
    -0.53
     Himo
    -0.53
     traite
    -0.52
    POSITIVE LOGITS
     autorytatywna
    0.77
     each
    0.63
     them
    0.58
     these
    0.57
    requireNonNull
    0.56
    +#+#
    0.56
     every
    0.53
     CreateTagHelper
    0.52
    tanleria
    0.50
    Bibliograf
    0.50
    Act Density 0.311%

    No Known Activations