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

    Neuronpedia

    INDEX
    Explanations

    Code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лас
    -0.07
    _cr
    -0.06
     Statements
    -0.06
     Kre
    -0.06
     Bulg
    -0.06
    46
    -0.06
     DIS
    -0.06
     coli
    -0.06
    Led
    -0.06
     Cham
    -0.06
    POSITIVE LOGITS
     conquest
    0.06
    gist
    0.06
    ыџN
    0.06
     ener
    0.06
    _env
    0.06
     mining
    0.06
     unittest
    0.06
     passive
    0.05
    案
    0.05
     pathMatch
    0.05
    Act Density 0.021%

    No Known Activations