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
     духов
    -0.06
    CustomLabel
    -0.06
     ово
    -0.06
    …)↵↵
    -0.06
    =".$
    -0.06
     суспіль
    -0.06
    }}">↵
    -0.06
    _gl
    -0.06
    .screen
    -0.06
     HALF
    -0.06
    POSITIVE LOGITS
    Tensor
    0.07
    USE
    0.07
     sortie
    0.07
    -functions
    0.07
     carbonate
    0.07
     reloading
    0.06
    un
    0.06
     arising
    0.06
     homelessness
    0.06
    水
    0.06
    Act Density 0.000%

    No Known Activations