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

    Neuronpedia

    INDEX
    Explanations

    voice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .plist
    -0.08
    Bank
    -0.06
    expenses
    -0.06
    �
    -0.06
    Brazil
    -0.06
    .ini
    -0.06
     Ferrari
    -0.06
    ULATOR
    -0.06
    �
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     herkes
    0.07
    _penalty
    0.06
     fundament
    0.06
    -origin
    0.06
    (us
    0.06
    -rounded
    0.06
    );
↵
↵
↵
    0.06
    _MATH
    0.06
     statically
    0.06
     Dün
    0.06
    Act Density 0.004%

    No Known Activations