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

    Neuronpedia

    INDEX
    Explanations

    impulse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tweaking
    -0.07
    ़न
    -0.06
     thick
    -0.06
     innocent
    -0.06
    桃
    -0.06
     fille
    -0.06
     cancer
    -0.06
    illaume
    -0.06
     theat
    -0.06
     सच
    -0.06
    POSITIVE LOGITS
     impulse
    0.15
     impulses
    0.13
     impuls
    0.08
     compulsory
    0.08
    衝
    0.07
     Routes
    0.07
     Series
    0.07
    いつ
    0.07
     compuls
    0.07
    ;(
    0.07
    Act Density 0.002%

    No Known Activations