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

    Neuronpedia

    INDEX
    Explanations

    code comparison operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adapt
    -0.07
    Lou
    -0.07
    .fhir
    -0.07
     aging
    -0.07
     Cancel
    -0.07
    字符串
    -0.07
     passion
    -0.07
     Passion
    -0.07
     Adapt
    -0.07
     VX
    -0.06
    POSITIVE LOGITS
    iesen
    0.07
    築
    0.07
    піон
    0.06
    ved
    0.06
    atched
    0.06
     Đại
    0.06
    $('
    0.06
    #from
    0.06
    noticed
    0.06
     assaulted
    0.05
    Act Density 0.001%

    No Known Activations