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

    Neuronpedia

    INDEX
    Explanations

    problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ॉक
    -0.07
    �
    -0.06
     Cave
    -0.06
     observation
    -0.06
    Indexes
    -0.06
    _AT
    -0.06
    设
    -0.06
     net
    -0.06
    tour
    -0.06
    .Att
    -0.06
    POSITIVE LOGITS
    Ｄ
    0.07
    _settings
    0.07
     sped
    0.06
     reactionary
    0.06
     ~
    0.06
    склад
    0.06
     Assistance
    0.06
     مساحت
    0.06
    -led
    0.06
    Its
    0.06
    Act Density 0.086%

    No Known Activations