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

    Neuronpedia

    INDEX
    Explanations

    text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     articulate
    -0.07
     modify
    -0.06
     Tell
    -0.06
     Venezuela
    -0.06
    baz
    -0.06
     effectively
    -0.06
     nf
    -0.06
    _MASTER
    -0.06
     content
    -0.06
     Schools
    -0.06
    POSITIVE LOGITS
    FilterWhere
    0.07
    InInspector
    0.07
    県
    0.07
    arta
    0.07
    :%
    0.07
    ано
    0.07
    业
    0.06
    oken
    0.06
    chi
    0.06
    义
    0.06
    Act Density 0.000%

    No Known Activations