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

    Neuronpedia

    INDEX
    Explanations

    memorial site

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cursory
    0.51
     devast
    0.49
     Summers
    0.48
     indign
    0.47
     vremena
    0.46
     exquisitely
    0.46
     épouse
    0.46
     devastated
    0.45
    人文
    0.45
     introductions
    0.45
    POSITIVE LOGITS
    Massage
    0.53
    ättning
    0.49
    System
    0.49
    Medical
    0.49
    Rotation
    0.47
    Velocity
    0.46
     મિત
    0.46
    Monitoring
    0.45
    Cascade
    0.45
     मस
    0.45
    Act Density 0.002%

    No Known Activations