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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     hiss
    -0.06
    /sign
    -0.06
    _extraction
    -0.06
    edor
    -0.06
    _stat
    -0.06
    자를
    -0.06
     vědom
    -0.06
    ุตบอล
    -0.06
    妃
    -0.06
    POSITIVE LOGITS
    APON
    0.07
     Mathematics
    0.07
     Modes
    0.07
     Damage
    0.07
    ?.
    0.06
    ้ค
    0.06
     Guild
    0.06
     impeccable
    0.06
     От
    0.06
     guild
    0.06
    Act Density 0.000%

    No Known Activations