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

    Neuronpedia

    INDEX
    Explanations

    let us followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -*/
    0.42
     funnel
    0.40
     tack
    0.38
    phan
    0.35
     got
    0.34
     aline
    0.34
    abhut
    0.34
    decrypt
    0.34
     *}(
    0.33
     zj
    0.33
    POSITIVE LOGITS
     Biz
    0.41
    Ｖ
    0.41
     V
    0.41
    V
    0.39
    Outdoor
    0.39
    <0xC5>
    0.38
     Biên
    0.38
     Konink
    0.37
     ING
    0.37
     Assistance
    0.36
    Act Density 0.001%

    No Known Activations