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

    Neuronpedia

    INDEX
    Explanations

    lack of options or escape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     χρει
    0.42
    Lonely
    0.41
     universal
    0.41
     universality
    0.40
    Needed
    0.38
    Should
    0.37
     perlu
    0.37
     필요
    0.37
     Universal
    0.37
    Universal
    0.37
    POSITIVE LOGITS
     recourse
    0.88
     choice
    0.76
    choice
    0.75
     chance
    0.70
     выхода
    0.69
     recours
    0.68
     escape
    0.67
     salida
    0.66
     alternativas
    0.66
     hope
    0.65
    Act Density 0.014%

    No Known Activations