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

    Neuronpedia

    INDEX
    Explanations

    Date and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hazards
    0.48
    oine
    0.48
     ambientales
    0.46
    seti
    0.46
     Balliye
    0.46
    gmail
    0.45
     Steward
    0.45
    gelt
    0.45
     искать
    0.45
     effectually
    0.44
    POSITIVE LOGITS
     pumpkins
    0.43
     poetic
    0.43
     measured
    0.41
     lap
    0.41
    וד
    0.40
     rotation
    0.40
     galloping
    0.40
     bl
    0.40
     pathway
    0.39
     pumpkin
    0.39
    Act Density 0.000%

    No Known Activations