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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alimentaires
    -0.56
    TintMode
    -0.56
    CloseOperation
    -0.55
     Norden
    -0.53
     masculina
    -0.51
     liitty
    -0.51
     mathematician
    -0.51
    ConstraintMaker
    -0.50
    rungsseite
    -0.50
    éhez
    -0.49
    POSITIVE LOGITS
    tonsoft
    0.54
    UserScript
    0.53
    =−
    0.52
     lenker
    0.51
     Bib
    0.50
    urel
    0.50
    Становништво
    0.50
     hela
    0.50
     virtual
    0.50
    virtual
    0.49
    Act Density 0.001%

    No Known Activations