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

    Neuronpedia

    INDEX
    Explanations

    references to "head" in the context of physical objects or mechanisms

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

    head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.73
     utafitiHapana
    -0.70
    AutoScaleMode
    -0.67
     CreateTagHelper
    -0.66
    AnchorStyles
    -0.66
    出版年
    -0.65
     estekak
    -0.65
    tagHelperRunner
    -0.63
     الحره
    -0.63
    Tikang
    -0.63
    POSITIVE LOGITS
     head
    0.77
     Head
    0.69
     heads
    0.59
     HEAD
    0.58
    Head
    0.56
     cabeça
    0.49
     Heads
    0.48
     cabezas
    0.46
     cabeza
    0.46
     kepala
    0.46
    Act Density 0.009%

    No Known Activations