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

    Neuronpedia

    INDEX
    Explanations

    Math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lhs
    -0.07
    Fi
    -0.07
    thresh
    -0.07
    _Sh
    -0.06
    -tip
    -0.06
    _FL
    -0.06
     lig
    -0.06
    CEO
    -0.06
    .Agent
    -0.06
    _sh
    -0.06
    POSITIVE LOGITS
     mainly
    0.07
    -Methods
    0.06
     biển
    0.06
     حضور
    0.06
     doctoral
    0.06
     paed
    0.06
     FormGroup
    0.06
    contr
    0.06
     nomin
    0.06
    .Excel
    0.06
    Act Density 0.024%

    No Known Activations