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

    Neuronpedia

    INDEX
    Explanations

    First person realization/decision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     מאוד
    -0.07
     applied
    -0.07
     expressed
    -0.07
    redno
    -0.07
    alse
    -0.07
    allero
    -0.07
    Applied
    -0.07
    Sum
    -0.07
    odos
    -0.07
     angew
    -0.07
    POSITIVE LOGITS
     überhaupt
    0.10
     ?>/
    0.09
     vowed
    0.09
     sildenafil
    0.08
    这么
    0.08
     Lola
    0.08
     irrev
    0.08
     الكبرى
    0.08
     prêmio
    0.08
    恋
    0.08
    Act Density 0.092%

    No Known Activations