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

    Neuronpedia

    INDEX
    Explanations

    negative numerals or values

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

    indices near boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }])
    -0.37
    __))
    -0.37
     mxArray
    -0.36
    ]))
    -0.36
    ]})
    -0.35
    adaptiveStyles
    -0.35
    verwijspagina
    -0.35
    }))
    -0.34
    aarrggbb
    -0.34
    ())))
    -0.32
    POSITIVE LOGITS
     AssemblyCulture
    0.72
     محفوظة
    0.53
    ConstraintMaker
    0.51
    errHandler
    0.50
    日至
    0.49
     CURIAM
    0.49
    ginate
    0.47
    imageshack
    0.47
     препратки
    0.46
    relenting
    0.46
    Act Density 0.024%

    No Known Activations