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

    Neuronpedia

    INDEX
    Explanations

    stolen kisses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    те
    0.76
    y
    0.75
    iveness
    0.72
    а
    0.68
    的東西
    0.68
    то
    0.68
    й
    0.68
    allax
    0.67
     rectangle
    0.66
    emie
    0.66
    POSITIVE LOGITS
     unsatisfied
    0.93
     adrift
    0.92
    asambhavam
    0.84
     bystanders
    0.79
     sweeteners
    0.79
     Limerick
    0.78
     приобре
    0.77
     Subsidi
    0.77
     subsidiaries
    0.76
     sardines
    0.76
    Act Density 0.000%

    No Known Activations