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

    Neuronpedia

    INDEX
    Explanations

    versatile tool

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    分别
    0.48
    .
    0.46
    و
    0.46
     Raman
    0.44
    ال
    0.43
     dz
    0.42
     Dane
    0.42
     Director
    0.41
     ز
    0.41
     Moto
    0.41
    POSITIVE LOGITS
    CHEMY
    0.54
    Expires
    0.50
     stateMutability
    0.50
    𝗚
    0.49
    Benzoimidazol
    0.48
    (";
    0.48
    Beyblade
    0.48
    Proxy
    0.48
    CString
    0.48
    ವಿಲ್ಲ
    0.48
    Act Density 0.001%

    No Known Activations