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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     слу
    -0.07
    —even
    -0.07
    ろ
    -0.06
    Instr
    -0.06
    sWith
    -0.06
    ‡
    -0.06
    ONENT
    -0.06
     pasado
    -0.06
    Develop
    -0.06
    //---------------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
    icontains
    0.07
    ulle
    0.07
    .navigate
    0.07
     Frankfurt
    0.07
     парамет
    0.06
     charcoal
    0.06
     Distributed
    0.06
     Diagnostic
    0.06
    >V
    0.06
     courage
    0.06
    Act Density 0.002%

    No Known Activations