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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ssl
    -0.07
     think
    -0.07
    vil
    -0.06
    Min
    -0.06
    _CLIENT
    -0.06
     DIC
    -0.06
     therapies
    -0.06
    述
    -0.06
    04
    -0.06
     інших
    -0.06
    POSITIVE LOGITS
     elektr
    0.07
     resultat
    0.07
     rifles
    0.06
     personalised
    0.06
     bicycles
    0.06
     asla
    0.06
    ジャ
    0.06
    ดน
    0.06
     درباره
    0.06
     Mutation
    0.06
    Act Density 0.000%

    No Known Activations