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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conduc
    -0.07
    *out
    -0.06
     حتى
    -0.06
    *&
    -0.06
    ectors
    -0.06
    etype
    -0.06
     suo
    -0.06
    .edu
    -0.06
    _abstract
    -0.06
     Schedule
    -0.06
    POSITIVE LOGITS
    	a
    0.07
    /mp
    0.07
    953
    0.06
     fft
    0.06
     Photon
    0.06
    OAuth
    0.06
    قات
    0.06
    ा।↵↵
    0.06
    _IN
    0.06
     アイ
    0.06
    Act Density 0.000%

    No Known Activations