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

    Neuronpedia

    INDEX
    Explanations

    only transformed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     उर्वशी
    0.58
     pursuance
    0.56
    foresaid
    0.52
    ູ່
    0.51
    holomorphic
    0.51
    FBSDKError
    0.51
    лович
    0.50
    ຯ
    0.50
     sultry
    0.50
     Fakultas
    0.49
    POSITIVE LOGITS
    J
    0.58
    /
    0.57
    B
    0.56
    -
    0.55
     plant
    0.54
    I
    0.53
     plants
    0.53
     [
    0.52
     (
    0.52
    *
    0.52
    Act Density 0.000%

    No Known Activations