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

    Neuronpedia

    INDEX
    Explanations

    disgust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     волод
    -0.07
    겠다
    -0.07
    (chat
    -0.06
     Parallel
    -0.06
     والأ
    -0.06
     ult
    -0.06
     گست
    -0.06
     भव
    -0.06
     �
    -0.06
     difícil
    -0.06
    POSITIVE LOGITS
     disgust
    0.08
    asley
    0.07
    体
    0.07
    0.07
    -known
    0.07
     annoyance
    0.07
    Replace
    0.07
     provisioning
    0.07
     drove
    0.07
    isko
    0.06
    Act Density 0.009%

    No Known Activations