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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional statements related to context or variability

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

    depending on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.40
     sorella
    -0.37
     SPIRIT
    -0.36
     bitte
    -0.36
    Mentions
    -0.36
     ""],
    -0.35
    ivably
    -0.35
     crying
    -0.35
     mascota
    -0.34
     Chwiliwch
    -0.34
    POSITIVE LOGITS
    depending
    0.82
     depending
    0.77
    depends
    0.75
     tergantung
    0.73
     depends
    0.73
     dependiendo
    0.68
     Depending
    0.68
    Depending
    0.67
     depend
    0.65
     depende
    0.65
    Act Density 0.321%

    No Known Activations