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

    Neuronpedia

    INDEX
    Explanations

    phrases describing visual perceptions or comparisons

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

    describing what something looks like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ambién
    -0.39
    Máy
    -0.30
     deoarece
    -0.29
    Portale
    -0.29
     gydy
    -0.29
     festgestellt
    -0.29
    occasione
    -0.28
     recomendado
    -0.28
     demasiado
    -0.28
     замі
    -0.27
    POSITIVE LOGITS
    delwed
    0.83
    EndInit
    0.74
    IUrlHelper
    0.69
    bootstrapcdn
    0.66
     PhpStorm
    0.65
    VersionUID
    0.61
    AnchorTagHelper
    0.60
    IntoConstraints
    0.59
    SourceChecksum
    0.59
     Itself
    0.59
    Act Density 0.006%

    No Known Activations