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

    Neuronpedia

    INDEX
    Explanations

    utf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     windowHeight
    -0.07
    _iters
    -0.07
    よね
    -0.07
    pbs
    -0.06
     الإسلام
    -0.06
     entrega
    -0.06
    _shop
    -0.06
    koneksi
    -0.06
    老
    -0.06
     InetAddress
    -0.06
    POSITIVE LOGITS
     Aim
    0.08
    utf
    0.06
    “Yes
    0.06
     accusation
    0.06
     reputation
    0.06
     wit
    0.06
    vides
    0.06
    career
    0.06
     METH
    0.06
     handing
    0.06
    Act Density 0.000%

    No Known Activations