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

    Neuronpedia

    INDEX
    Explanations

    contradictions and contrasts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Μετα
    -0.06
     Curso
    -0.06
     Pope
    -0.06
    	rep
    -0.06
    aporation
    -0.06
     آزمون
    -0.06
     triang
    -0.06
    .uf
    -0.06
    [data
    -0.06
    yper
    -0.06
    POSITIVE LOGITS
    nst
    0.07
     DEST
    0.07
    `:
    0.07
    whel
    0.06
     glGet
    0.06
     uncomfortable
    0.06
    ¸
    0.06
     kel
    0.06
    ennessee
    0.06
    าร
    0.06
    Act Density 0.138%

    No Known Activations