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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to capability and performance

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

    Capable of [doing something]

    np_acts-logits-general · gemini-2.0-flash

    can do / capable of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     visiter
    -0.48
     част
    -0.48
     conhecer
    -0.48
    pyx
    -0.47
    ]")]
    -0.46
    eseorang
    -0.45
     regioni
    -0.44
    Try
    -0.44
     conoscere
    -0.44
    нар
    -0.44
    POSITIVE LOGITS
     withstand
    0.80
     cope
    0.66
     tolerate
    0.65
    GEBURTSDATUM
    0.65
     handling
    0.64
     PyTuple
    0.64
    createServer
    0.62
    forChild
    0.61
     manage
    0.61
    \{\\
    0.61
    Act Density 0.239%

    No Known Activations