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

    Neuronpedia

    INDEX
    Explanations

    late or latent followed by time or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pellet
    0.93
     moor
    0.87
    িং
    0.82
    sung
    0.81
     mop
    0.80
     platelets
    0.79
    designer
    0.77
     carpet
    0.77
     Collar
    0.77
     нет
    0.77
    POSITIVE LOGITS
    comer
    1.38
    comers
    1.32
     lamented
    1.30
    OpenCamera
    0.96
    plit
    0.95
    یکس
    0.94
     gratification
    0.93
    ו
    0.92
    いました
    0.91
    Fees
    0.90
    Act Density 0.072%

    No Known Activations