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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )f
    -0.07
     certain
    -0.07
     fasc
    -0.07
    _then
    -0.07
     móc
    -0.06
    :X
    -0.06
     Christine
    -0.06
    _generate
    -0.06
    perf
    -0.06
    ivery
    -0.06
    POSITIVE LOGITS
     Insights
    0.08
    (place
    0.07
    NamedQuery
    0.07
     empez
    0.07
    봽
    0.07
    ระหว
    0.07
     campaigning
    0.07
    quiry
    0.07
     Increment
    0.07
     Reason
    0.07
    Act Density 0.004%

    No Known Activations