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

    Neuronpedia

    INDEX
    Explanations

    few options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    condensation
    0.95
    collectionView
    0.94
    RECTION
    0.93
    ioners
    0.93
    ியின்
    0.91
    girlfriend
    0.91
    вають
    0.91
    eture
    0.90
    hong
    0.88
    ceding
    0.88
    POSITIVE LOGITS
     O
    0.85
     S
    0.81
    ...
    0.80
     Universal
    0.77
     root
    0.75
     أ
    0.73
     L
    0.73
     tij
    0.73
     B
    0.72
     R
    0.71
    Act Density 0.004%

    No Known Activations