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

    Neuronpedia

    INDEX
    Explanations

    instances of conflict or decision-making scenarios

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

    Preceding a comma, "so", or parenthesis

    np_acts-logits-general · gemini-2.0-flash

    if so, then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ようになりました
    -0.35
    tagHelperRunner
    -0.35
     always
    -0.35
    んですよ
    -0.34
    шру
    -0.33
     Curve
    -0.33
    NOPQRST
    -0.32
     []).
    -0.32
    GTCX
    -0.31
     dieną
    -0.31
    POSITIVE LOGITS
    Personendaten
    0.59
    SBATCH
    0.56
    RTCK
    0.54
    saraba
    0.52
    #+#
    0.50
    fjspx
    0.49
    Aiheesta
    0.47
    CppCodeGen
    0.47
     مرئيه
    0.47
    AddTagHelper
    0.46
    Act Density 0.285%

    No Known Activations