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

    Neuronpedia

    INDEX
    Explanations

    до

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (two
    -0.09
    <Type
    -0.08
    (length
    -0.08
    <any
    -0.08
    (single
    -0.08
    _depend
    -0.08
    (State
    -0.08
    (hidden
    -0.07
     >(
    -0.07
     états
    -0.07
    POSITIVE LOGITS
     Nadia
    0.10
     cedo
    0.09
     baz
    0.08
     EDT
    0.08
    уни
    0.08
     gigantic
    0.08
     Julius
    0.08
     Nixon
    0.08
     odio
    0.08
     GMT
    0.08
    Act Density 0.002%

    No Known Activations