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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ParseException
    -0.07
     Pist
    -0.07
    ockey
    -0.07
    =z
    -0.07
    Congress
    -0.06
    >A
    -0.06
    旌
    -0.06
     Ramp
    -0.06
    ène
    -0.06
     depiction
    -0.06
    POSITIVE LOGITS
    交友
    0.08
    igidBody
    0.07
    就够了
    0.07
    ambient
    0.07
    _friend
    0.07
    _↵
    0.07
    社群
    0.06
    Scope
    0.06
    _infos
    0.06
    ɸ
    0.06
    Act Density 0.072%

    No Known Activations