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

    Neuronpedia

    INDEX
    Explanations

    website navigation links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     titles
    0.40
     overhe
    0.39
    βάλ
    0.38
    grat
    0.38
    ニコ
    0.38
    idname
    0.38
    denes
    0.38
    imak
    0.38
    rable
    0.37
    alpine
    0.37
    POSITIVE LOGITS
    <a>
    0.68
     <
    0.46
    Guides
    0.41
    Guide
    0.40
     Guide
    0.37
    ND
    0.36
     〈
    0.36
    <u>
    0.36
    Libraries
    0.36
    =<
    0.36
    Act Density 0.000%

    No Known Activations