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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lion
    -0.06
     Pis
    -0.06
    (fun
    -0.06
    Paused
    -0.06
     impedance
    -0.06
    ával
    -0.06
     мех
    -0.06
    弹
    -0.06
    言わ
    -0.06
    024
    -0.06
    POSITIVE LOGITS
     nachází
    0.07
    htags
    0.07
     geht
    0.07
    erta
    0.06
    enable
    0.06
    ัท
    0.06
    estimated
    0.06
    ...↵↵↵↵
    0.06
    hcp
    0.06
    烧
    0.06
    Act Density 0.000%

    No Known Activations