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

    Neuronpedia

    INDEX
    Explanations

    birthday following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    де
    0.85
    ğraf
    0.85
     এরপর
    0.83
     무엇
    0.81
    iveness
    0.80
    ң
    0.77
     malah
    0.76
    kt
    0.75
     아름
    0.74
    ⎞
    0.73
    POSITIVE LOGITS
    succ
    0.85
     earphones
    0.83
     passant
    0.82
     gout
    0.80
    𝗶
    0.77
     intoxicated
    0.77
    Наи
    0.77
     શકો
    0.76
     hostage
    0.75
     санк
    0.75
    Act Density 0.005%

    No Known Activations