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
     ود
    -0.07
     Sammy
    -0.07
     сегодня
    -0.07
    logradouro
    -0.07
     pisc
    -0.07
     imp
    -0.07
     timings
    -0.06
     venue
    -0.06
    _DIRECT
    -0.06
    masters
    -0.06
    POSITIVE LOGITS
     riots
    0.07
    (formData
    0.07
    분석
    0.06
    黄
    0.06
    一级
    0.06
     weakness
    0.06
    读
    0.06
    未
    0.06
    wayne
    0.06
    _checkbox
    0.06
    Act Density 0.003%

    No Known Activations