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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ln
    -0.07
     newcom
    -0.07
    ोर
    -0.06
    里面
    -0.06
    LineEdit
    -0.06
     kcal
    -0.06
    ng
    -0.06
     dần
    -0.06
    vw
    -0.06
    oo
    -0.06
    POSITIVE LOGITS
     frequency
    0.07
     written
    0.06
    Alle
    0.06
    _COMMAND
    0.06
     digital
    0.06
     ∀
    0.06
    -commit
    0.06
     soci
    0.06
    odia
    0.06
    лаб
    0.06
    Act Density 0.004%

    No Known Activations