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

    Neuronpedia

    INDEX
    Explanations

    logical structures and conditional statements in programming code

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

    both. both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MathML
    -0.56
    addComponent
    -0.53
    \{\\
    -0.52
     TPP
    -0.48
     Scra
    -0.48
     समीक्षाएं
    -0.47
    rager
    -0.47
    gage
    -0.46
    lable
    -0.45
    }}}}
    -0.45
    POSITIVE LOGITS
     båda
    0.59
     begge
    0.52
    aarrggbb
    0.51
    IntoConstraints
    0.50
     Beide
    0.48
     respiración
    0.47
     cooperación
    0.45
     antigüedad
    0.45
     ambas
    0.45
     sensibilidad
    0.45
    Act Density 0.022%

    No Known Activations