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

    Neuronpedia

    INDEX
    Explanations

    references to significant actions or changes

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

    describing an action or change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.58
    GEBURTSDATUM
    -0.52
    cshtml
    -0.47
     canst
    -0.46
    ſelves
    -0.45
     disambiguazione
    -0.43
     RIPRODUZIONE
    -0.42
    nocache
    -0.41
     reprodu
    -0.40
     Infórmanos
    -0.40
    POSITIVE LOGITS
     move
    1.48
    move
    1.27
     Move
    1.20
    Move
    1.20
     moves
    1.13
     MOVE
    1.09
    MOVE
    1.04
    moves
    1.00
     Moves
    0.99
     moved
    0.90
    Act Density 0.008%

    No Known Activations