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

    Neuronpedia

    INDEX
    Explanations

    freeze onto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     turn
    0.85
     finitely
    0.83
     সদস্য
    0.78
     creditor
    0.76
     contrad
    0.74
     cunt
    0.73
     typographic
    0.72
     purchaser
    0.71
     Purchaser
    0.70
    ATUS
    0.70
    POSITIVE LOGITS
    लीवुड
    0.72
    Pov
    0.70
    oglio
    0.69
    lai
    0.68
    oplane
    0.68
    night
    0.67
    Sind
    0.67
     relayed
    0.66
    ær
    0.66
    ableness
    0.65
    Act Density 0.000%

    No Known Activations