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

    Neuronpedia

    INDEX
    Explanations

    Pref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     husband
    -0.07
    jadi
    -0.07
    _SOUND
    -0.07
     domain
    -0.06
    _slots
    -0.06
    Stock
    -0.06
    елич
    -0.06
    	hash
    -0.06
     than
    -0.06
     salad
    -0.06
    POSITIVE LOGITS
     Pref
    0.07
     FDA
    0.07
    yped
    0.06
     PREF
    0.06
     Pornhub
    0.06
     depending
    0.06
    인이
    0.06
     bố
    0.06
    Towards
    0.06
    .Fl
    0.06
    Act Density 0.001%

    No Known Activations