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

    Neuronpedia

    INDEX
    Explanations

    family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dessins
    -0.08
    	refresh
    -0.08
     Equity
    -0.08
     Century
    -0.08
     Question
    -0.08
    ancestor
    -0.08
     clueless
    -0.08
     Estates
    -0.07
     toppen
    -0.07
     Thickness
    -0.07
    POSITIVE LOGITS
     ਇਕ
    0.09
    including
    0.08
    お
    0.08
     revolves
    0.08
    投入
    0.08
     idyllic
    0.07
     including
    0.07
     matters
    0.07
     prosp
    0.07
    營
    0.07
    Act Density 0.022%

    No Known Activations