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

    Neuronpedia

    INDEX
    Explanations

    Code or chat logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ])),↵
    -0.07
     phen
    -0.07
     bean
    -0.07
    pickle
    -0.06
    [field
    -0.06
    ӝ
    -0.06
     leur
    -0.06
     которой
    -0.06
    戋
    -0.06
    펩
    -0.06
    POSITIVE LOGITS
    קשר
    0.07
    orsi
    0.07
    modal
    0.07
    社会保险
    0.07
    .optional
    0.07
     Gladiator
    0.07
    丽江
    0.07
     Falls
    0.07
    Digit
    0.07
     anonymous
    0.07
    Act Density 0.037%

    No Known Activations