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

    Neuronpedia

    INDEX
    Explanations

    code and programming terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oid
    -0.07
     Hein
    -0.07
    explain
    -0.07
     criter
    -0.06
    gens
    -0.06
     unbelievable
    -0.06
    ACCESS
    -0.06
    ernity
    -0.06
    /St
    -0.06
     Derby
    -0.06
    POSITIVE LOGITS
    755
    0.07
     hlavu
    0.07
    ="--
    0.06
    ActionCode
    0.06
     появ
    0.06
     İtalya
    0.06
    236
    0.06
    767
    0.06
    341
    0.06
     )↵↵↵
    0.06
    Act Density 0.000%

    No Known Activations