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

    Neuronpedia

    INDEX
    Explanations

    Woody

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snake
    -0.06
     consultations
    -0.06
    ibu
    -0.06
    ician
    -0.06
    ladatel
    -0.06
     resonance
    -0.06
     administering
    -0.06
    地球
    -0.06
    nce
    -0.06
     breasts
    -0.05
    POSITIVE LOGITS
    	AL
    0.07
     REALLY
    0.06
     Cox
    0.06
    (mid
    0.06
     Woody
    0.06
     и
    0.06
    'S
    0.06
     사람들이
    0.06
    HomeAs
    0.06
    _True
    0.06
    Act Density 0.001%

    No Known Activations