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

    Neuronpedia

    INDEX
    Explanations

    actions and emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    менте
    0.66
     নির্দিষ্ট
    0.65
     নিশ্চিত
    0.64
     determining
    0.63
     modific
    0.62
     biztos
    0.60
     forecasting
    0.59
    addington
    0.59
     determines
    0.59
     ബ്രി
    0.59
    POSITIVE LOGITS
     smile
    0.72
     cry
    0.69
     toug
    0.68
     moan
    0.67
     splurge
    0.63
    Die
    0.62
     die
    0.61
     fight
    0.61
    Fight
    0.60
     eat
    0.60
    Act Density 0.198%

    No Known Activations