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

    Neuronpedia

    INDEX
    Explanations

    If

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iç
    -0.07
     phoenix
    -0.06
    Fr
    -0.06
    (Control
    -0.06
     DACA
    -0.06
     accrued
    -0.06
    business
    -0.06
    /tools
    -0.06
    ّ
    -0.06
     vardı
    -0.06
    POSITIVE LOGITS
    너
    0.08
     carnival
    0.07
     nelle
    0.07
    rpm
    0.06
    ební
    0.06
    ulario
    0.06
     elasticity
    0.06
    ButtonModule
    0.06
    nano
    0.06
    Thinking
    0.06
    Act Density 0.000%

    No Known Activations