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

    Neuronpedia

    INDEX
    Explanations

    points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pose
    -0.07
     decade
    -0.06
    878
    -0.06
     econ
    -0.06
    इस
    -0.06
     observations
    -0.06
     cryptographic
    -0.06
    (output
    -0.06
     rég
    -0.05
    ），
    -0.05
    POSITIVE LOGITS
    Unused
    0.07
    .currentState
    0.07
     actresses
    0.07
    ombres
    0.07
     стал
    0.06
     Adventures
    0.06
    /small
    0.06
    しま
    0.06
    PCM
    0.06
    Không
    0.06
    Act Density 0.004%

    No Known Activations