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

    Neuronpedia

    INDEX
    Explanations

    uk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (enemy
    -0.07
    τολ
    -0.07
     هر
    -0.07
    +'
    -0.07
    이버
    -0.07
    Рё
    -0.07
     vardı
    -0.07
     усл
    -0.06
     zví
    -0.06
    /print
    -0.06
    POSITIVE LOGITS
    uto
    0.06
     Food
    0.06
    odic
    0.06
     pref
    0.06
     Coron
    0.06
    _HELPER
    0.06
    Photos
    0.06
     quotes
    0.06
     elucid
    0.06
    super
    0.06
    Act Density 0.000%

    No Known Activations