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

    Neuronpedia

    INDEX
    Explanations

    Code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AUTO
    -0.07
    _look
    -0.07
    켜
    -0.06
    Registr
    -0.06
    commended
    -0.06
     περιο
    -0.06
    houses
    -0.06
    ěstí
    -0.06
    ("{}
    -0.06
     expects
    -0.06
    POSITIVE LOGITS
     tagging
    0.06
    Dating
    0.06
    licos
    0.06
     полити
    0.06
     visions
    0.06
     update
    0.06
     */,
    0.06
    andidate
    0.06
     collects
    0.06
     taxes
    0.06
    Act Density 0.000%

    No Known Activations