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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating legal stipulations and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    原始内容存档于
    -0.52
    ----</
    -0.51
    Xna
    -0.50
    bufio
    -0.49
    Bibliograf
    -0.48
    userdetails
    -0.47
     BoxDecoration
    -0.47
    Composable
    -0.46
    RetentionPolicy
    -0.46
    oneofs
    -0.46
    POSITIVE LOGITS
    否
    0.34
     pelajaran
    0.32
     vyst
    0.32
    icznie
    0.32
     deinem
    0.32
    InputTagHelper
    0.32
    évaluateur
    0.31
    bbene
    0.30
     Talmud
    0.30
     dibutuhkan
    0.30
    Act Density 0.067%

    No Known Activations