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

    Neuronpedia

    INDEX
    Explanations

    Violent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corners
    -0.07
     معرفی
    -0.07
     frogs
    -0.07
    Ｏ
    -0.07
     dusk
    -0.06
     deniz
    -0.06
     indexing
    -0.06
    Rules
    -0.06
    quee
    -0.06
    луж
    -0.06
    POSITIVE LOGITS
     %↵
    0.08
    ''↵
    0.07
     newPosition
    0.07
     violently
    0.07
    Autowired
    0.06
     MonoBehaviour
    0.06
     hungry
    0.06
     conducting
    0.06
     Effective
    0.06
     diese
    0.06
    Act Density 0.012%

    No Known Activations