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
     rapes
    -0.07
     ""}↵
    -0.07
     monitor
    -0.07
     transforms
    -0.06
    572
    -0.06
     immigrant
    -0.06
    waters
    -0.06
    ()↵↵↵↵
    -0.06
    but
    -0.06
    (paths
    -0.06
    POSITIVE LOGITS
     RSVP
    0.08
    っち
    0.07
    یکی
    0.07
    _stdio
    0.07
     olduğuna
    0.06
    락
    0.06
     Shorts
    0.06
    Skin
    0.06
    ingga
    0.06
    YTE
    0.06
    Act Density 0.000%

    No Known Activations