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

    Neuronpedia

    INDEX
    Explanations

    students

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ir
    -0.07
    'ı
    -0.07
     worksheet
    -0.07
     lateral
    -0.07
     adventurers
    -0.07
    arness
    -0.06
     optic
    -0.06
     �
    -0.06
    (cal
    -0.06
     future
    -0.06
    POSITIVE LOGITS
    *******/↵
    0.06
    .replace
    0.06
    .getStart
    0.06
     Searching
    0.06
     حکم
    0.06
     earners
    0.06
     deflect
    0.06
     bör
    0.06
    .isUser
    0.06
    ЎыџN
    0.06
    Act Density 0.044%

    No Known Activations