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

    Neuronpedia

    INDEX
    Explanations

    .iter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    něm
    -0.07
     sollen
    -0.07
     ett
    -0.07
     involves
    -0.07
    lying
    -0.07
    、​
    -0.06
    >>::
    -0.06
     Osaka
    -0.06
     pastors
    -0.06
     slang
    -0.06
    POSITIVE LOGITS
    INDOW
    0.06
     embryos
    0.06
    experiment
    0.06
     fila
    0.06
    oux
    0.06
    cstdlib
    0.06
     Estados
    0.06
     швидко
    0.06
    agner
    0.06
     Programme
    0.06
    Act Density 0.020%

    No Known Activations