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

    Neuronpedia

    INDEX
    Explanations

    Eric

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SimpleName
    -0.07
    玳
    -0.07
     Went
    -0.07
    觃
    -0.07
     Bened
    -0.07
    盎
    -0.07
    бли
    -0.07
    uesday
    -0.07
    ammed
    -0.07
     Speedway
    -0.07
    POSITIVE LOGITS
     operational
    0.07
     |\
    0.07
    وتر
    0.07
     protección
    0.06
     incarcerated
    0.06
     suppose
    0.06
     equipment
    0.06
    protected
    0.06
    -\
    0.06
     disrupting
    0.06
    Act Density 0.007%

    No Known Activations