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

    Neuronpedia

    INDEX
    Explanations

    human experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gain
    -0.07
     Claud
    -0.07
    if
    -0.07
    ỹ
    -0.07
    _training
    -0.06
    NM
    -0.06
    Timer
    -0.06
    ーダ
    -0.06
    240
    -0.06
    _fp
    -0.06
    POSITIVE LOGITS
     которых
    0.06
    OCUMENT
    0.06
    dur
    0.06
    ads
    0.06
    @Column
    0.06
    emia
    0.06
    우
    0.06
     kne
    0.06
    stime
    0.06
    _PLAN
    0.06
    Act Density 0.144%

    No Known Activations