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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _av
    -0.08
     Gourmet
    -0.08
     الأسعار
    -0.08
    visitor
    -0.08
    Has
    -0.08
    umise
    -0.07
     capables
    -0.07
     رابطه
    -0.07
    .callbacks
    -0.07
    ేవ
    -0.07
    POSITIVE LOGITS
     imprisonment
    0.12
     sentenced
    0.11
     prison
    0.11
     punishment
    0.10
     probation
    0.10
     sentencing
    0.10
    刑
    0.10
     rehabilitation
    0.10
     jail
    0.10
     convictions
    0.10
    Act Density 0.015%

    No Known Activations