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

    Neuronpedia

    INDEX
    Explanations

    H

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spectacle
    -0.07
    iana
    -0.07
    벤트
    -0.07
    х
    -0.06
    Fx
    -0.06
    achat
    -0.06
     kterých
    -0.06
    _deep
    -0.06
     같습니다
    -0.06
    ++)
↵
    -0.06
    POSITIVE LOGITS
     fake
    0.07
    ifiant
    0.06
    Secret
    0.06
     Dump
    0.06
     comprised
    0.06
     amazing
    0.06
     hollow
    0.06
    .Select
    0.06
    โซ
    0.06
    _CAST
    0.06
    Act Density 0.026%

    No Known Activations