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

    Neuronpedia

    INDEX
    Explanations

    disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <tr
    -0.06
    Interesting
    -0.06
     numeric
    -0.06
    (annotation
    -0.06
    Distribution
    -0.06
    .initialize
    -0.06
    -sample
    -0.06
    略
    -0.06
    购
    -0.06
    Pokemon
    -0.06
    POSITIVE LOGITS
    ,alpha
    0.07
     Vor
    0.07
    -floating
    0.07
     arz
    0.07
     emailing
    0.06
    UBLE
    0.06
     cara
    0.06
     Nigel
    0.06
     AutoMapper
    0.06
    abit
    0.06
    Act Density 0.007%

    No Known Activations