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

    Neuronpedia

    INDEX
    Explanations

    hesitation and stammering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    还得
    0.80
     grise
    0.78
     sake
    0.77
     tune
    0.77
     pousse
    0.76
    ún
    0.74
     hubby
    0.73
    needed
    0.72
    ème
    0.71
    unité
    0.70
    POSITIVE LOGITS
    ⋯
    1.22
    ...!
    1.07
    ..!
    1.02
     congratulated
    1.01
    \...
    1.01
     elucidated
    0.96
    […]
    0.96
    GLFW
    0.94
    …</
    0.94
    🥺
    0.93
    Act Density 0.014%

    No Known Activations