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

    Neuronpedia

    INDEX
    Explanations

    client creation code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㺫
    0.45
     alkenyl
    0.44
     échelle
    0.41
     ಅನುಪಾತ
    0.40
     почвы
    0.40
    勂
    0.39
    CER
    0.38
    <unused31>
    0.38
    頖
    0.38
    칡
    0.38
    POSITIVE LOGITS
    client
    0.47
    Arc
    0.46
     client
    0.45
    phone
    0.40
     Arc
    0.38
    clients
    0.38
     clients
    0.38
    loop
    0.37
    encia
    0.36
    fan
    0.36
    Act Density 0.007%

    No Known Activations