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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical notation and expressions

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

    Mathematical or logical notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical variables and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.87
     Verſ
    -0.86
    MLLoader
    -0.85
     imagui
    -0.83
    ConstraintMaker
    -0.82
     témoig
    -0.82
    脚注の使い方
    -0.81
    нгред
    -0.80
    tonode
    -0.78
     queſto
    -0.77
    POSITIVE LOGITS
    GenerationType
    0.27
     stride
    0.26
    本
    0.24
    之
    0.23
    lookahead
    0.22
    容量
    0.22
     umgangssprach
    0.22
     budget
    0.22
     size
    0.21
     alone
    0.21
    Act Density 1.656%

    No Known Activations