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

    Neuronpedia

    INDEX
    Explanations

    localhost

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @Api
    -0.08
    (rep
    -0.07
    predicted
    -0.07
    (SYS
    -0.07
    产业园
    -0.07
     implemented
    -0.07
    ("(%
    -0.07
    Slot
    -0.07
    -Agent
    -0.07
    电价
    -0.07
    POSITIVE LOGITS
     Cardio
    0.08
     Straight
    0.07
     withstand
    0.07
     Hebrew
    0.07
     Crossing
    0.07
    challenge
    0.06
    ircraft
    0.06
    -download
    0.06
    _tx
    0.06
     notorious
    0.06
    Act Density 0.008%

    No Known Activations