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

    Neuronpedia

    INDEX
    Explanations

    liability or being harmless

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fue
    -0.07
     Aluminum
    -0.06
    795
    -0.06
    Software
    -0.06
    -k
    -0.06
     tế
    -0.06
     together
    -0.06
    imators
    -0.06
    문화
    -0.06
     AU
    -0.06
    POSITIVE LOGITS
    
    0.07
    illegal
    0.07
    ี่
    0.07
    ôte
    0.07
     Spread
    0.07
     nurturing
    0.06
     shady
    0.06
    .De
    0.06
    -banner
    0.06
    .Items
    0.06
    Act Density 0.013%

    No Known Activations