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

    Neuronpedia

    INDEX
    Explanations

    small, simple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     되는
    -0.07
    .save
    -0.07
     homicides
    -0.06
    受
    -0.06
    ारक
    -0.06
    Backend
    -0.06
     ISP
    -0.06
     jerk
    -0.06
    -speaking
    -0.06
    _hop
    -0.06
    POSITIVE LOGITS
    	kfree
    0.07
    _TOOLTIP
    0.06
    归
    0.06
     зн
    0.06
    .Ass
    0.06
     Emerging
    0.06
    alaria
    0.05
     suitable
    0.05
     neighb
    0.05
    andering
    0.05
    Act Density 0.040%

    No Known Activations