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

    Neuronpedia

    INDEX
    Explanations

    items after "like"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    droid
    0.46
    uillez
    0.44
     ब्लैक
    0.43
    দ্বীপ
    0.42
    糸
    0.42
    tywn
    0.42
    damn
    0.42
     రోజు
    0.42
     keel
    0.42
     შე
    0.41
    POSITIVE LOGITS
     xen
    0.45
    Scholar
    0.43
    Diethyl
    0.42
     conjunt
    0.38
     Galilee
    0.38
     estr
    0.37
     diethyl
    0.37
     enriqu
    0.37
     assin
    0.37
     Worm
    0.36
    Act Density 0.000%

    No Known Activations