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

    Neuronpedia

    INDEX
    Explanations

    experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    303
    -0.06
    acional
    -0.06
    _sleep
    -0.06
    Finite
    -0.06
    <Int
    -0.06
     شو
    -0.06
     nudity
    -0.06
     increasingly
    -0.06
    pecies
    -0.06
    िथ
    -0.06
    POSITIVE LOGITS
    .hit
    0.07
    .gs
    0.06
     všichni
    0.06
     Rec
    0.06
     Jeb
    0.06
    ******/
    0.06
     Included
    0.06
     verschiedene
    0.06
    yre
    0.06
    reference
    0.06
    Act Density 0.026%

    No Known Activations