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

    Neuronpedia

    INDEX
    Explanations

    tangent half-angle substitution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แน
    -0.09
    Logger
    -0.08
     dolphins
    -0.08
     dinosaur
    -0.08
     logger
    -0.07
    Dc
    -0.07
     HMS
    -0.07
     Dynamo
    -0.07
     morce
    -0.07
     discrimination
    -0.07
    POSITIVE LOGITS
    ::*;↵
    0.08
    技巧
    0.08
    译
    0.08
    ::*;↵↵
    0.08
     있으
    0.08
    ?";↵
    0.07
     merits
    0.07
    __/
    0.07
     �
    0.07
    uš
    0.07
    Act Density 0.010%

    No Known Activations