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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Auch
    -0.07
    ++]
    -0.07
    ιστή
    -0.06
     morality
    -0.06
    ully
    -0.06
    кою
    -0.06
    }↵↵↵↵↵
    -0.06
    Ang
    -0.06
    owy
    -0.06
    por
    -0.06
    POSITIVE LOGITS
    Verified
    0.07
     Travis
    0.07
     Mali
    0.07
     Gregg
    0.06
     Greg
    0.06
     Brigade
    0.06
     فرمود
    0.06
    cycle
    0.06
     Missile
    0.06
    alloc
    0.06
    Act Density 0.054%

    No Known Activations