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

    Neuronpedia

    INDEX
    Explanations

    grants vs. other funding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =”
    0.42
     Gregg
    0.40
    ∗</
    0.39
    کل
    0.39
     ELE
    0.38
     zond
    0.38
    IPL
    0.38
     OWL
    0.38
    élé
    0.38
    вле
    0.38
    POSITIVE LOGITS
    okovic
    0.40
    钰
    0.37
    dpy
    0.37
     controlling
    0.37
    ರೂ
    0.36
     შ
    0.35
    ugen
    0.35
     cursory
    0.35
     indifferent
    0.34
    uerung
    0.34
    Act Density 0.000%

    No Known Activations