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

    Neuronpedia

    INDEX
    Explanations

    programming language constructs and conditional statements

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

    Code or configuration snippets

    np_acts-logits-general · gemini-2.0-flash

    data encoding and parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MN
    -0.66
     Minnesota
    -0.63
    matchCondition
    -0.61
    MIN
    -0.60
    Minneapolis
    -0.58
    ArrowToggle
    -0.58
     Minneapolis
    -0.58
    Minnesota
    -0.58
     Henne
    -0.56
    MN
    -0.55
    POSITIVE LOGITS
     صوتيه
    0.76
     الحره
    0.70
    oton
    0.57
     huyền
    0.54
     Issue
    0.52
    })->
    0.52
     InputDecoration
    0.52
    tvguidetime
    0.51
     >>=
    0.51
    ########.
    0.51
    Act Density 0.166%

    No Known Activations