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

    Neuronpedia

    INDEX
    Explanations

    base pairing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ent
    -0.06
    ’aut
    -0.06
     داریم
    -0.06
    303
    -0.06
    blogs
    -0.06
     protagonists
    -0.06
    FS
    -0.06
    .student
    -0.06
    productId
    -0.06
    .fi
    -0.06
    POSITIVE LOGITS
     lovely
    0.06
    -events
    0.06
     taper
    0.06
     recent
    0.06
    券
    0.06
     ห
    0.06
    。一
    0.06
     hairs
    0.06
    PACE
    0.06
    {\
    0.06
    Act Density 0.004%

    No Known Activations