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

    Neuronpedia

    INDEX
    Explanations

    tell me about a time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    事実
    0.46
     sourire
    0.44
     individui
    0.43
    可能な
    0.42
     smile
    0.41
     संभावित
    0.41
     സാധ്യത
    0.39
     ممكن
    0.39
     mídia
    0.38
    whether
    0.38
    POSITIVE LOGITS
     overcoming
    1.00
     experiences
    0.88
     spending
    0.76
     adventures
    0.75
     overcomes
    0.74
     getting
    0.71
     преодо
    0.70
     discovering
    0.70
     experiencias
    0.70
     overcame
    0.70
    Act Density 0.017%

    No Known Activations