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

    Neuronpedia

    INDEX
    Explanations

    articles followed by adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сегодня
    0.35
     sequentially
    0.35
     definitively
    0.34
     indefinitely
    0.34
    のように
    0.34
     completely
    0.33
     overwhelmingly
    0.32
     inexplic
    0.32
    oluminescence
    0.32
     qualitatively
    0.31
    POSITIVE LOGITS
     watery
    0.56
     joyful
    0.51
     joyous
    0.46
     mighty
    0.46
     wondrous
    0.46
     ardent
    0.44
     starry
    0.44
     grassy
    0.40
     earthly
    0.40
     misty
    0.40
    Act Density 0.090%

    No Known Activations