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

    Neuronpedia

    INDEX
    Explanations

    concepts related to feature selection methods in data classification

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

    solely, explicitly rather than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.41
    bav
    -0.40
    WriteAttribute
    -0.37
    htbp
    -0.37
    nonumber
    -0.36
    PU
    -0.36
    äf
    -0.36
     memu
    -0.35
     Perc
    -0.35
    ecu
    -0.34
    POSITIVE LOGITS
     informée
    0.59
     abstrato
    0.54
    󠁴
    0.51
    kijken
    0.50
     abstracto
    0.50
    Enllaços
    0.50
     recours
    0.49
    httphttps
    0.47
     Italij
    0.47
     inherently
    0.47
    Act Density 0.118%

    No Known Activations