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

    Neuronpedia

    INDEX
    Explanations

    spiders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    运行
    -0.07
    th
    -0.06
    .sav
    -0.06
     ri
    -0.06
     rut
    -0.06
    xad
    -0.06
     mansion
    -0.06
    ::$
    -0.05
    kem
    -0.05
    letes
    -0.05
    POSITIVE LOGITS
    ινό
    0.07
    .todo
    0.07
     ELEMENT
    0.07
     motions
    0.06
    珠
    0.06
    _services
    0.06
     sorts
    0.06
    (create
    0.06
    (=
    0.06
     django
    0.06
    Act Density 0.020%

    No Known Activations