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

    Neuronpedia

    INDEX
    Explanations

    say "omes"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     até
    -0.07
     righteousness
    -0.07
    てしまった
    -0.07
     Lightning
    -0.07
     tracing
    -0.07
     autocomplete
    -0.07
     Charlie
    -0.06
    ᡞ
    -0.06
     chicken
    -0.06
    .prototype
    -0.06
    POSITIVE LOGITS
    �
    0.08
    啧
    0.07
    :id
    0.07
    患有
    0.07
     CFR
    0.07
    less
    0.07
     đổi
    0.07
    呕
    0.07
    react
    0.07
    meg
    0.07
    Act Density 0.001%

    No Known Activations