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

    Neuronpedia

    INDEX
    Explanations

    Unstructured/informal content or code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _children
    -0.06
     oz
    -0.06
    dog
    -0.06
     ček
    -0.06
    ae
    -0.06
    supply
    -0.06
    lower
    -0.06
     defeating
    -0.06
     adolescents
    -0.06
    prob
    -0.05
    POSITIVE LOGITS
     unlock
    0.08
     Association
    0.07
    (recv
    0.07
    IMPLIED
    0.06
    izzling
    0.06
    iso
    0.06
    (jq
    0.06
    rowsable
    0.06
     Milwaukee
    0.06
    oca
    0.06
    Act Density 0.004%

    No Known Activations