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

    Neuronpedia

    INDEX
    Explanations

    Sam

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     теперь
    -0.07
     Photographer
    -0.06
     二
    -0.06
    	dp
    -0.06
    ’il
    -0.06
     Bad
    -0.06
    collector
    -0.06
     Po
    -0.06
     Wheeler
    -0.06
    ----------
    -0.06
    POSITIVE LOGITS
     Checking
    0.07
    _cells
    0.07
    廷
    0.06
    -lived
    0.06
    662
    0.06
    ovně
    0.06
     habits
    0.06
    _meta
    0.06
    (filtered
    0.06
    anzi
    0.06
    Act Density 0.004%

    No Known Activations