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

    Neuronpedia

    INDEX
    Explanations

    names and authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.16
    ;
    0.16
    said
    0.16
    {
    0.15
    1
    0.15
    any
    0.15
    а
    0.15
    5
    0.15
    e
    0.14
    ↵
    0.14
    POSITIVE LOGITS
     nymphs
    0.15
     Carnaval
    0.14
     amphib
    0.14
     aberrations
    0.14
     mutations
    0.14
     péd
    0.14
     glam
    0.14
     sirens
    0.14
     polyp
    0.13
     goût
    0.13
    Act Density 0.000%

    No Known Activations