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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pinpoint
    -0.07
    270
    -0.07
     lobby
    -0.06
     Wien
    -0.06
    ụp
    -0.06
     LH
    -0.06
    _Con
    -0.06
    .com
    -0.06
     handler
    -0.06
    해
    -0.06
    POSITIVE LOGITS
    ческие
    0.07
    ,proto
    0.07
     ((__
    0.06
    opping
    0.06
    웨디시
    0.06
     इसक
    0.06
     примен
    0.06
     budd
    0.06
    //=
    0.06
    ność
    0.06
    Act Density 0.005%

    No Known Activations