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

    Neuronpedia

    INDEX
    Explanations

    symbols and notations used in mathematical equations and expressions

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

    LaTeX formatting within mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    `(-1)` power notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PARE
    -0.45
    hime
    -0.45
    び
    -0.44
     Roz
    -0.44
     Iglesia
    -0.44
     channe
    -0.42
    etts
    -0.41
    Prin
    -0.41
     Gra
    -0.41
     Bar
    -0.41
    POSITIVE LOGITS
    )^
    0.98
    )^{
    0.88
    )**
    0.85
    }^
    0.85
    )²
    0.83
    })^
    0.80
    })^{
    0.80
    }^{
    0.76
    WriteBarrier
    0.73
    ]^
    0.73
    Act Density 2.147%

    No Known Activations