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

    Neuronpedia

    INDEX
    Explanations

    Questions and conversational snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.84
     ModelExpression
    -0.71
    ThroughAttribute
    -0.64
    ruptedException
    -0.59
    posedge
    -0.57
     Мексичка
    -0.57
     الرياضيه
    -0.57
     esternos
    -0.57
     nakalista
    -0.56
     resourceCulture
    -0.53
    POSITIVE LOGITS
     Those
    0.54
     A
    0.50
     Prost
    0.49
    बंध
    0.49
     Satellite
    0.49
    adă
    0.48
     The
    0.48
     Overnight
    0.47
     Some
    0.46
     Your
    0.46
    Act Density 0.010%

    No Known Activations