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

    Neuronpedia

    INDEX
    Explanations

    intimidation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ảo
    -0.07
    ải
    -0.07
    Wind
    -0.07
    출
    -0.07
    unto
    -0.07
     Due
    -0.07
    转换
    -0.07
    計
    -0.07
     Apex
    -0.07
     spring
    -0.07
    POSITIVE LOGITS
     homeowner
    0.08
     intimidating
    0.08
    工业园
    0.08
    こんに
    0.07
     whistlebl
    0.07
     بص
    0.07
     intimidation
    0.07
    퓔
    0.07
    ば
    0.07
     قائلا
    0.07
    Act Density 0.004%

    No Known Activations