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

    Neuronpedia

    INDEX
    Explanations

    testing something

    np_max-act · gemini-2.0-flash

    guidelines and constraints for developing a project.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ORA
    -0.07
     أنه
    -0.07
    ora
    -0.06
     rod
    -0.06
    dance
    -0.06
     Helpers
    -0.06
     Lobby
    -0.06
    .misc
    -0.06
    Textures
    -0.06
    んです
    -0.06
    POSITIVE LOGITS
     regiment
    0.06
    (diff
    0.06
     "..
    0.06
     ${↵
    0.06
     출
    0.06
    еного
    0.06
    推
    0.06
    مارات
    0.06
     wrap
    0.06
    attrib
    0.06
    Act Density 0.035%

    No Known Activations