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

    Neuronpedia

    INDEX
    Explanations

    metrics related to online engagement or interaction

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

    foreign words or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.59
    thâu
    -0.52
    LLocation
    -0.51
    AutoScaleMode
    -0.49
    NTIS
    -0.46
     NavController
    -0.46
     früheren
    -0.44
     lizenzfreies
    -0.44
     incomplète
    -0.44
     houſe
    -0.43
    POSITIVE LOGITS
    <?
    0.40
    ellite
    0.37
    >{@
    0.37
     Zwer
    0.35
    !*\
    0.34
     chung
    0.34
    biamo
    0.33
     rzecz
    0.33
    álat
    0.33
    ELSE
    0.33
    Act Density 0.005%

    No Known Activations