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

    Neuronpedia

    INDEX
    Explanations

    references to specific concentrations and measurements in scientific contexts

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

    concentrations and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.63
    ViewFeatures
    -0.63
    LookAnd
    -0.63
     Chwiliwch
    -0.56
    Tikang
    -0.56
    <?
    -0.54
    ⟬
    -0.53
    -0.53
    :✨
    -0.52
     للاسماء
    -0.51
    POSITIVE LOGITS
     concentration
    0.69
     Concentration
    0.61
     concentración
    0.60
    concentration
    0.59
    Concentration
    0.59
     Konzentration
    0.58
     концентра
    0.57
     concentrations
    0.57
     CONCENT
    0.55
     Concentrations
    0.54
    Act Density 0.170%

    No Known Activations