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

    Neuronpedia

    INDEX
    Explanations

    key actions or processes related to improving health or wellness

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

    describing, finding, detecting, capturing, negotiating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitVars
    -0.69
     հղումներ
    -0.68
    rrggbb
    -0.64
    DIPSETTING
    -0.64
    AlterField
    -0.53
    IVEREF
    -0.52
    énario
    -0.52
     SwitchCompat
    -0.52
    rungsseite
    -0.51
    harapkan
    -0.51
    POSITIVE LOGITS
     stuff
    0.35
     tem
    0.34
     vis
    0.32
     dra
    0.32
    rady
    0.31
    ORNING
    0.30
    àu
    0.29
     aw
    0.29
     tes
    0.29
     Sure
    0.29
    Act Density 0.138%

    No Known Activations