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

    Neuronpedia

    INDEX
    Explanations

    studies and their findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     representa
    0.88
     иллюстрация
    0.83
     representations
    0.79
     representation
    0.76
     manifestaciones
    0.75
     manifestations
    0.74
     signified
    0.74
     embod
    0.74
    รษฐกิจ
    0.73
     manifestation
    0.73
    POSITIVE LOGITS
     conducted
    1.65
     investigating
    1.53
     examining
    1.49
     investigated
    1.43
     published
    1.41
     conducting
    1.37
     examined
    1.36
     investigates
    1.32
    conduct
    1.30
     investigate
    1.28
    Act Density 0.349%

    No Known Activations