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

    Neuronpedia

    INDEX
    Explanations

    +=

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     говорить
    -0.07
     yg
    -0.07
     interviewing
    -0.06
    ψης
    -0.06
    erusform
    -0.06
    ίλ
    -0.06
     yıl
    -0.06
     درخواست
    -0.06
    "):
↵
    -0.06
     hafta
    -0.06
    POSITIVE LOGITS
    /pay
    0.07
    _he
    0.06
     ej
    0.06
    insi
    0.06
    _preference
    0.06
    _uniform
    0.06
     плав
    0.06
     Ear
    0.06
     metab
    0.06
     exploding
    0.06
    Act Density 0.003%

    No Known Activations