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

    Neuronpedia

    INDEX
    Explanations

    mentions of formatting directives and operations for output in programming

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

    C++ iostream library

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.80
    mybatisplus
    -0.64
     calendriers
    -0.59
    BufferException
    -0.58
     laude
    -0.58
    ocino
    -0.53
    transQ
    -0.53
    Gön
    -0.51
     ISNI
    -0.50
    olescence
    -0.49
    POSITIVE LOGITS
     تضيفلها
    0.68
     purpoſe
    0.66
     Jefus
    0.64
    }.
    0.63
    multirow
    0.60
    ]='\
    0.60
     Conscience
    0.59
    }');
    0.59
    ]').
    0.59
     ſtate
    0.58
    Act Density 0.002%

    No Known Activations