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

    Neuronpedia

    INDEX
    Explanations

    hypersensitivity reactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oceans
    -0.07
    	Random
    -0.07
    できない
    -0.07
     vl
    -0.06
     stride
    -0.06
     FFT
    -0.06
     SESSION
    -0.06
    决定
    -0.06
    rito
    -0.06
     ammo
    -0.06
    POSITIVE LOGITS
     enhancement
    0.07
     円
    0.06
     Gain
    0.06
    ізнес
    0.06
     Enhancement
    0.06
    äs
    0.06
     Till
    0.06
     питання
    0.06
     корол
    0.06
    (utf
    0.06
    Act Density 0.001%

    No Known Activations