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

    Neuronpedia

    INDEX
    Explanations

    utilities setup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مساعد
    -0.09
    (Mockito
    -0.08
     يوسف
    -0.08
     ნ
    -0.08
     ذکر
    -0.08
     шақ
    -0.08
    heses
    -0.08
    nað
    -0.08
     يې
    -0.08
    ರಿಗೆ
    -0.08
    POSITIVE LOGITS
     insurance
    0.08
    Per
    0.07
     antimicrobial
    0.07
     Per
    0.07
     defense
    0.07
     biometric
    0.07
    _RANDOM
    0.07
    ષ
    0.06
     threat
    0.06
     professions
    0.06
    Act Density 0.001%

    No Known Activations