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

    Neuronpedia

    INDEX
    Explanations

    adopt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weakening
    -0.08
     dní
    -0.06
     querying
    -0.06
     Cache
    -0.06
    alking
    -0.06
    gün
    -0.06
     decreases
    -0.06
    ]]:↵
    -0.06
    _Session
    -0.06
     funcs
    -0.06
    POSITIVE LOGITS
    ير
    0.07
    출장안마
    0.07
    (withIdentifier
    0.07
    647
    0.07
     gifs
    0.06
    =G
    0.06
    387
    0.06
    648
    0.06
    246
    0.06
     LIC
    0.06
    Act Density 0.004%

    No Known Activations