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

    Neuronpedia

    INDEX
    Explanations

    Police/legal reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encouragement
    -0.06
     diplomacy
    -0.06
    �
    -0.06
    odd
    -0.06
    ults
    -0.06
     AC
    -0.06
     BX
    -0.06
    OG
    -0.06
    ymoon
    -0.06
     ל
    -0.06
    POSITIVE LOGITS
     Remove
    0.07
    servers
    0.06
    (schema
    0.06
    )=>
    0.06
    (push
    0.06
     δημο
    0.06
     Conspiracy
    0.06
    Means
    0.06
    (current
    0.06
    寧
    0.06
    Act Density 0.040%

    No Known Activations