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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LOOKUP
    -0.08
     haber
    -0.07
     Twice
    -0.07
     круп
    -0.07
    adastro
    -0.06
    	ch
    -0.06
    xcd
    -0.06
    амет
    -0.06
     İki
    -0.06
    iles
    -0.06
    POSITIVE LOGITS
    ธน
    0.07
     spoon
    0.06
     interpersonal
    0.06
    566
    0.06
    qp
    0.06
    181
    0.06
    luv
    0.06
    886
    0.06
    918
    0.06
    bbc
    0.06
    Act Density 0.152%

    No Known Activations