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

    Neuronpedia

    INDEX
    Explanations

    policies and treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     computerScore
    0.75
     chalk
    0.71
     knelt
    0.69
     mark
    0.65
     scene
    0.64
    side
    0.63
     brand
    0.60
     song
    0.60
     house
    0.60
     écoul
    0.60
    POSITIVE LOGITS
    </h4>
    0.90
     Traits
    0.85
     Library
    0.82
     vayan
    0.80
    入力
    0.77
     Oberfläche
    0.76
     Walls
    0.75
     vassals
    0.74
     Gestión
    0.74
     निधी
    0.74
    Act Density 0.000%

    No Known Activations