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

    Neuronpedia

    INDEX
    Explanations

    file formats and structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     achter
    -0.08
    操纵
    -0.07
     busy
    -0.07
    缩
    -0.07
    贷
    -0.07
     счет
    -0.07
     wiring
    -0.07
     ZZ
    -0.06
    .gz
    -0.06
    *)((
    -0.06
    POSITIVE LOGITS
    變
    0.07
    fäh
    0.06
    -themed
    0.06
    .ModelForm
    0.06
    贫困户
    0.06
    ALAR
    0.06
    爱人
    0.06
     etwas
    0.06
    atters
    0.06
    TM
    0.06
    Act Density 0.077%

    No Known Activations