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

    Neuronpedia

    INDEX
    Explanations

    third

    np_max-act · gemini-2.0-flash

    mathematical expressions and operations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    STANCE
    -0.06
     cells
    -0.06
    pants
    -0.06
    ियल
    -0.06
    Ease
    -0.06
    zano
    -0.06
    peater
    -0.06
    dao
    -0.06
     Panels
    -0.06
    欠
    -0.06
    POSITIVE LOGITS
     ciphertext
    0.07
     благодаря
    0.07
     �
    0.07
     genuine
    0.06
    lah
    0.06
    ③
    0.06
     printing
    0.06
     persistence
    0.06
     глав
    0.06
     Northwestern
    0.06
    Act Density 0.000%

    No Known Activations