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

    Neuronpedia

    INDEX
    Explanations

    Figure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⇌
    -0.07
    /close
    -0.07
    compose
    -0.07
     Blow
    -0.07
     angered
    -0.07
    [Math
    -0.07
     getInfo
    -0.07
    离职
    -0.07
     cười
    -0.07
    .receive
    -0.06
    POSITIVE LOGITS
    弯
    0.07
    産
    0.07
     enabling
    0.07
     gratuita
    0.07
     VM
    0.06
    ViewItem
    0.06
     flux
    0.06
     pioneering
    0.06
    文化
    0.06
     elite
    0.06
    Act Density 0.006%

    No Known Activations