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

    Neuronpedia

    INDEX
    Explanations

    unethical business practices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    redi
    -0.07
    INGTON
    -0.07
    iplinary
    -0.06
    getting
    -0.06
     Wednesday
    -0.06
     Yankee
    -0.06
    𫠜
    -0.06
     Dek
    -0.06
     gets
    -0.06
     состо
    -0.06
    POSITIVE LOGITS
    ]:↵↵↵
    0.08
    ≒
    0.08
     Fraud
    0.07
    ⌠
    0.07
    _WM
    0.07
     marches
    0.07
    -tip
    0.07
     clam
    0.07
    acr
    0.07
     awe
    0.07
    Act Density 0.039%

    No Known Activations