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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     국
    -0.06
     wang
    -0.06
    _AFTER
    -0.06
    Highlight
    -0.06
     Political
    -0.06
    >)
    -0.06
     singled
    -0.06
    egration
    -0.06
    .tile
    -0.06
     mama
    -0.06
    POSITIVE LOGITS
     Days
    0.06
     useful
    0.06
    .Constants
    0.06
    chooser
    0.06
     asympt
    0.06
     ensures
    0.06
    ----------
    0.06
    ают
    0.06
     Pepsi
    0.06
     Bayesian
    0.06
    Act Density 0.000%

    No Known Activations