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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    veillance
    -0.07
     operators
    -0.07
     eradicate
    -0.06
    ee
    -0.06
     Surveillance
    -0.06
    vv
    -0.06
    assel
    -0.06
    permissions
    -0.06
    _mo
    -0.06
     appalling
    -0.06
    POSITIVE LOGITS
    付き
    0.07
     受
    0.07
     vòng
    0.07
    ouse
    0.07
     puck
    0.06
     stalls
    0.06
    .containsKey
    0.06
     elems
    0.06
    .MAX
    0.06
     nă
    0.06
    Act Density 0.002%

    No Known Activations