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

    Neuronpedia

    INDEX
    Explanations

    _PTR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beginnings
    -0.06
     начале
    -0.06
    oldur
    -0.06
    ickness
    -0.06
    兴
    -0.06
    egan
    -0.06
    αρ
    -0.06
     نظامی
    -0.06
     Humans
    -0.06
    她的
    -0.06
    POSITIVE LOGITS
    .Stage
    0.07
     distinguishing
    0.07
    .setFocus
    0.07
     Prior
    0.07
    ,n
    0.07
    ,y
    0.06
    (formData
    0.06
    Tpl
    0.06
     nevě
    0.06
    -{
    0.06
    Act Density 0.000%

    No Known Activations