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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mys
    -0.07
    stp
    -0.07
    yun
    -0.06
    orthy
    -0.06
     محیط
    -0.06
     路
    -0.06
     �
    -0.06
     broth
    -0.06
    zed
    -0.06
    ابقات
    -0.06
    POSITIVE LOGITS
    .=
    0.08
    Charlotte
    0.07
    elsey
    0.06
    "><?=
    0.06
    cession
    0.06
    _Act
    0.06
    ["$
    0.06
     Essence
    0.06
    (($
    0.06
     Drawing
    0.06
    Act Density 0.239%

    No Known Activations