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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their mathematical relationships

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

    Mathematical or programming addition

    np_acts-logits-general · gemini-2.0-flash

    plus signs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sche
    -0.50
    }]$
    -0.45
    DEC
    -0.44
     \%}$
    -0.44
    IRA
    -0.43
    SEM
    -0.42
    kers
    -0.42
    yama
    -0.42
    /-/
    -0.41
    query
    -0.41
    POSITIVE LOGITS
    +
    1.52
     +
    1.41
    +:+
    1.21
     plus
    1.13
    plus
    1.07
    ThroughAttribute
    1.06
    +.
    1.06
     $+
    1.05
     Plus
    1.05
    >+</
    1.05
    Act Density 0.314%

    No Known Activations