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

    Neuronpedia

    INDEX
    Explanations

    phrases with "edit" and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Descripcion
    0.47
    Churn
    0.46
    proved
    0.44
    Mitt
    0.43
    ሂ
    0.43
     বসবাসের
    0.42
    hip
    0.42
    itzen
    0.42
     invoke
    0.42
     fichero
    0.41
    POSITIVE LOGITS
    し
    0.53
     Malays
    0.48
    পা
    0.48
     ナイ
    0.48
    対応
    0.48
     Malaysia
    0.47
    L
    0.46
    yyati
    0.46
     WI
    0.46
    K
    0.46
    Act Density 0.002%

    No Known Activations