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

    Neuronpedia

    INDEX
    Explanations

    Academic citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mak
    -0.07
    Spacing
    -0.07
     miệng
    -0.07
    TIME
    -0.06
    CH
    -0.06
     Dear
    -0.06
    ARCH
    -0.06
     cousin
    -0.06
     Sour
    -0.06
    ΟΡ
    -0.06
    POSITIVE LOGITS
    -states
    0.06
    trib
    0.06
     viewDidLoad
    0.06
     ();
    0.06
    yect
    0.06
    -St
    0.06
     InvalidOperationException
    0.06
    ++)
↵
    0.06
    estimate
    0.06
    _contr
    0.06
    Act Density 0.043%

    No Known Activations