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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    혼
    -0.07
    	Created
    -0.07
    迥
    -0.07
    .API
    -0.07
     incompet
    -0.07
     anew
    -0.07
     Sự
    -0.07
    _dropdown
    -0.07
    _quality
    -0.06
     предостав
    -0.06
    POSITIVE LOGITS
     sparse
    0.08
    -src
    0.07
     Positive
    0.06
    част
    0.06
    PLICATE
    0.06
    ±
    0.06
    -----
    0.06
     Ces
    0.06
     loading
    0.06
     sufficient
    0.06
    Act Density 0.000%

    No Known Activations