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

    Neuronpedia

    INDEX
    Explanations

    references to specific cases or situations

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

    conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    disposing
    -0.44
     tartalomajánló
    -0.40
    rrggbb
    -0.38
    BagLayout
    -0.36
     alcanzado
    -0.32
    omentos
    -0.32
    ="../../
    -0.30
     estekak
    -0.30
    tvguidetime
    -0.30
    crollView
    -0.30
    POSITIVE LOGITS
    既然
    0.68
     skoro
    0.53
    новниш
    0.51
     dezelve
    0.51
    干脆
    0.51
    SBATCH
    0.51
     solteiro
    0.49
     zoude
    0.48
     asam
    0.47
    OLEAN
    0.46
    Act Density 0.081%

    No Known Activations