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

    Neuronpedia

    INDEX
    Explanations

    URLs and chapter numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嘬
    0.23
     vattum
    0.23
    𒊩
    0.22
     সরাস
    0.22
    𐰚
    0.21
    goài
    0.21
    ार्टमेंट
    0.21
    gramModel
    0.21
     অয়েল
    0.20
    ゥム
    0.20
    POSITIVE LOGITS
    0.34
    2
    0.26
     (
    0.25
     t
    0.24
    1
    0.24
    4
    0.24
    -
    0.24
     –
    0.23
     P
    0.22
     c
    0.22
    Act Density 0.014%

    No Known Activations