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

    Neuronpedia

    INDEX
    Explanations

    references to Java programming and UI-related elements

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

    code instantiation keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.55
     poveznice
    -0.48
     auroit
    -0.47
     feroit
    -0.45
    MessageTagHelper
    -0.44
    แล้ว
    -0.39
     pouvoit
    -0.39
     Geschä
    -0.38
    GenerationType
    -0.38
     noqa
    -0.37
    POSITIVE LOGITS
    Ӕ
    0.57
     surla
    0.51
    complexType
    0.49
     screw
    0.49
     Screw
    0.48
    Autoritní
    0.47
    fjspx
    0.47
     proc
    0.47
     informée
    0.47
     لب
    0.47
    Act Density 0.004%

    No Known Activations