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

    Neuronpedia

    INDEX
    Explanations

    He

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     after
    -0.07
     unintended
    -0.07
     wallet
    -0.07
     useRef
    -0.07
     spaced
    -0.07
     Experiment
    -0.07
     packet
    -0.06
     proprio
    -0.06
     algo
    -0.06
    야
    -0.06
    POSITIVE LOGITS
    toa
    0.07
    ","\
    0.06
     논
    0.06
     ю
    0.06
    Cell
    0.06
    inston
    0.06
    	buff
    0.06
    .Url
    0.05
    .enemy
    0.05
    _FAR
    0.05
    Act Density 0.000%

    No Known Activations