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

    Neuronpedia

    INDEX
    Explanations

    legal references and figures related to analysis or calculations

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

    code and technical references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OLAR
    -0.39
    IsMutable
    -0.39
    olar
    -0.38
    erb
    -0.38
    AutoScaleMode
    -0.38
    LookAnd
    -0.36
     /\.
    -0.36
     aller
    -0.36
    nomin
    -0.35
    kart
    -0.35
    POSITIVE LOGITS
    CppCodeGen
    0.48
     otomatig
    0.47
    __*/
    0.45
    paravant
    0.43
     EdgeInsets
    0.42
    valdi
    0.41
    BufferException
    0.41
    InjectAttribute
    0.41
     Савезне
    0.41
    DebuggerNonUser
    0.40
    Act Density 0.310%

    No Known Activations