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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itir
    -0.07
    ocab
    -0.07
     sollten
    -0.07
    绿
    -0.06
    /ca
    -0.06
     розрах
    -0.06
     أمر
    -0.06
     tribute
    -0.06
    jure
    -0.06
    けて
    -0.06
    POSITIVE LOGITS
    geometry
    0.07
    ddf
    0.07
    ombo
    0.07
     documenting
    0.07
     ≠
    0.06
    虚
    0.06
     toughness
    0.06
    Reviewed
    0.06
     IoT
    0.06
     china
    0.06
    Act Density 0.008%

    No Known Activations