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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aure
    -0.07
    .autoconfigure
    -0.06
    �
    -0.06
     Myers
    -0.06
    {{
    -0.06
     Буд
    -0.06
    един
    -0.06
     Mid
    -0.06
    iná
    -0.06
     steward
    -0.06
    POSITIVE LOGITS
     beforehand
    0.06
    ife
    0.06
     resultados
    0.06
     розроб
    0.06
    cmath
    0.06
    perm
    0.06
     nor
    0.06
    (tc
    0.06
    �
    0.06
    فی
    0.06
    Act Density 0.001%

    No Known Activations