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

    Neuronpedia

    INDEX
    Explanations

    mathematical definitions and theorems using "if and only if" statements

    oai_token-act-pair · gemini-2.0-flash

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ͅ
    -0.59
    Capítulo
    -0.58
    Dislikes
    -0.58
     ExecuteAsync
    -0.57
    berdayakan
    -0.57
     referenties
    -0.56
    middels
    -0.55
    expandindo
    -0.55
     dessutom
    -0.54
    usahaan
    -0.54
    POSITIVE LOGITS
     equivalence
    0.65
    lossal
    0.58
     equival
    0.57
    Equivalent
    0.57
    equi
    0.57
    equals
    0.56
    allclose
    0.56
    equivalent
    0.54
     Equivalent
    0.54
     Equi
    0.54
    Act Density 2.214%

    No Known Activations