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

    Neuronpedia

    INDEX
    Explanations

    glass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     machines
    -0.07
     Eight
    -0.07
     damping
    -0.07
     follic
    -0.07
     Record
    -0.07
    Period
    -0.06
    (foo
    -0.06
    Implementation
    -0.06
     Diagnosis
    -0.06
     oğ
    -0.06
    POSITIVE LOGITS
    ницу
    0.06
     성공
    0.06
     gearing
    0.06
    iç
    0.06
     paran
    0.06
     death
    0.06
     depending
    0.06
     interracial
    0.06
    وع
    0.06
    ítica
    0.06
    Act Density 0.006%

    No Known Activations