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

    Neuronpedia

    INDEX
    Explanations

    pm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mojo
    -0.07
    ariance
    -0.07
    _WRAPPER
    -0.07
     nedeni
    -0.07
    -engine
    -0.07
    -risk
    -0.07
    ysi
    -0.06
    Stat
    -0.06
    iyel
    -0.06
     "*"
    -0.06
    POSITIVE LOGITS
     npm
    0.08
    npm
    0.07
    pm
    0.07
    /npm
    0.07
     snap
    0.06
     murdered
    0.06
    ฟ
    0.06
     terminator
    0.06
    Arthur
    0.06
    ंब
    0.06
    Act Density 0.002%

    No Known Activations