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

    Neuronpedia

    INDEX
    Explanations

    theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    γά
    -0.07
    	jQuery
    -0.06
    モデル
    -0.06
    izedName
    -0.06
    clidean
    -0.06
    ')(
    -0.06
    capt
    -0.06
    *m
    -0.06
     soon
    -0.06
     catalyst
    -0.06
    POSITIVE LOGITS
     배우
    0.07
    (Utils
    0.06
    -bodied
    0.06
     खतर
    0.06
    /reference
    0.06
    bate
    0.06
     �
    0.06
    ละคร
    0.06
     abnormalities
    0.06
    sections
    0.06
    Act Density 0.014%

    No Known Activations