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

    Neuronpedia

    INDEX
    Explanations

    suspect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _space
    -0.08
     ayuda
    -0.07
     الرياض
    -0.07
    raise
    -0.07
    razy
    -0.07
     Easter
    -0.07
    éra
    -0.07
     Kolkata
    -0.06
     ROOM
    -0.06
    azio
    -0.06
    POSITIVE LOGITS
     suspected
    0.17
     suspect
    0.16
     suspects
    0.15
     suspicion
    0.12
     suspicions
    0.11
     Sus
    0.10
    Sus
    0.09
    sus
    0.09
     suspicious
    0.08
    疑
    0.08
    Act Density 0.008%

    No Known Activations