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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    омер
    -0.06
    ilians
    -0.06
    conti
    -0.06
    cede
    -0.06
    cwd
    -0.06
    .policy
    -0.06
    amin
    -0.06
     unanim
    -0.06
    уча
    -0.06
    оны
    -0.06
    POSITIVE LOGITS
     Deadly
    0.07
     ΑΓ
    0.07
    _REQUIRED
    0.07
    .onreadystatechange
    0.06
    _stage
    0.06
     she
    0.06
    TokenType
    0.06
    -show
    0.06
     conductor
    0.06
    _POS
    0.06
    Act Density 0.005%

    No Known Activations