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

    Neuronpedia

    INDEX
    Explanations

    Once

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     copies
    -0.06
     belirtilen
    -0.06
     dalla
    -0.06
    滑
    -0.06
     disabled
    -0.06
    ivity
    -0.06
     Indianapolis
    -0.06
     Dünya
    -0.06
     belli
    -0.06
    POSITIVE LOGITS
     once
    0.08
     Once
    0.08
    LES
    0.07
    IRECT
    0.07
    SCRIBE
    0.06
    .loss
    0.06
     předch
    0.06
    les
    0.06
    보고
    0.06
    (scene
    0.06
    Act Density 0.015%

    No Known Activations