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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diffs
    -0.06
    qi
    -0.06
    ет
    -0.06
    achi
    -0.06
     квар
    -0.06
     imagin
    -0.06
     genital
    -0.06
    oyo
    -0.06
     avi
    -0.06
    779
    -0.06
    POSITIVE LOGITS
    vy
    0.07
    .conditions
    0.07
    _pes
    0.07
    _ds
    0.07
    .getSelectionModel
    0.06
     快
    0.06
     месте
    0.06
    .Face
    0.06
    OPY
    0.06
     清
    0.06
    Act Density 0.008%

    No Known Activations