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

    Neuronpedia

    INDEX
    Explanations

    mind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     injections
    -0.07
    oler
    -0.07
    ausal
    -0.07
     Blonde
    -0.07
    อก
    -0.07
    urf
    -0.07
    📶
    -0.07
    ouch
    -0.07
    복
    -0.07
    _sound
    -0.07
    POSITIVE LOGITS
     mind
    0.08
    烻
    0.07
     לעומ
    0.07
    猹
    0.07
     الإمارات
    0.07
    榱
    0.07
    }",
    0.07
    rysler
    0.07
     كلم
    0.06
     الكمبي
    0.06
    Act Density 0.025%

    No Known Activations