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

    Neuronpedia

    INDEX
    Explanations

    destruction or integrity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     destruction
    -1.23
     integrity
    -1.23
    integrity
    -1.17
     Integrity
    -1.07
     Destruction
    -1.01
    Integrity
    -0.94
    destruction
    -0.91
     integridad
    -0.90
     compromised
    -0.85
    Destruction
    -0.81
    POSITIVE LOGITS
     AppBar
    0.53
    AnchorStyles
    0.53
     насељу
    0.50
    dani
    0.50
     aikaa
    0.50
    togen
    0.50
     inspired
    0.49
     fetched
    0.48
    یز
    0.48
     ibid
    0.48
    Act Density 0.111%

    No Known Activations