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

    Neuronpedia

    INDEX
    Explanations

    __

    np_max-act · gemini-2.0-flash

    technical terms and parameters related to software or programming environments.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    19
    -0.08
    aldo
    -0.08
    -0.08
    18
    -0.07
    583
    -0.07
    ID
    -0.07
    15
    -0.07
    57
    -0.07
    fds
    -0.07
    ild
    -0.07
    POSITIVE LOGITS
     __
    0.12
    (__
    0.11
     #__
    0.09
     (__
    0.08
     '__
    0.08
     Jonathan
    0.08
    Mom
    0.08
     __("
    0.08
     *__
    0.08
    ",__
    0.08
    Act Density 0.022%

    No Known Activations