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

    Neuronpedia

    INDEX
    Explanations

    measurements and dimensions of physical structures

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

    dimensions and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mijne
    -0.39
    digung
    -0.34
     omge
    -0.33
     supone
    -0.33
     löst
    -0.32
     sostuvo
    -0.32
     handen
    -0.31
     ajusta
    -0.31
     aarde
    -0.31
     Substanz
    -0.31
    POSITIVE LOGITS
     سكانية
    0.71
     BoxFit
    0.64
    IntoConstraints
    0.61
     tartalomajánló
    0.60
     ویکی‌پدی
    0.60
     CreateTagHelper
    0.59
     floor
    0.58
    BagLayout
    0.56
    posedge
    0.56
    хьтан
    0.55
    Act Density 0.005%

    No Known Activations