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

    Neuronpedia

    INDEX
    Explanations

    Scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     türlü
    -0.07
    uD
    -0.07
     Sağlık
    -0.07
     zách
    -0.07
     rb
    -0.06
    .month
    -0.06
    โปรแกรม
    -0.06
    Jud
    -0.06
    .borrow
    -0.06
    ']="
    -0.06
    POSITIVE LOGITS
    /gr
    0.07
     evolving
    0.07
     mano
    0.06
    237
    0.06
     interpretation
    0.06
     ery
    0.06
    フィ
    0.06
    每
    0.06
     registering
    0.06
    ofire
    0.06
    Act Density 0.001%

    No Known Activations