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

    Neuronpedia

    INDEX
    Explanations

    relates to, connection, caused by, use of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    la
    0.48
    ﺓ
    0.48
    ꔰ
    0.47
    ue
    0.47
    lı
    0.46
    르
    0.46
    eneral
    0.46
    ﺡ
    0.45
    idazol
    0.45
    찐
    0.45
    POSITIVE LOGITS
     oxidative
    0.43
    מש
    0.43
     pageant
    0.43
     mortgage
    0.42
    ENV
    0.42
     toddlers
    0.42
    襁
    0.42
     Spitzen
    0.41
     minimal
    0.41
     gegründet
    0.41
    Act Density 0.001%

    No Known Activations