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

    Neuronpedia

    INDEX
    Explanations

    it's important to note

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alebo
    0.80
     vagy
    0.80
    หรือ
    0.77
     또는
    0.77
     ضرور
    0.77
     hoặc
    0.76
     oppure
    0.74
    或其他
    0.74
     avulla
    0.74
     অথবা
    0.73
    POSITIVE LOGITS
     note
    1.70
     hear
    1.30
     remember
    1.30
     think
    1.21
    note
    1.21
     Note
    1.20
     consider
    1.19
     receive
    1.15
     imagine
    1.14
     have
    1.13
    Act Density 0.125%

    No Known Activations