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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lékař
    -0.07
    otre
    -0.07
     proč
    -0.06
    ‘
    -0.06
    ∧
    -0.06
    ــ
    -0.06
    爵
    -0.06
    “
    -0.06
     such
    -0.06
    <Entity
    -0.06
    POSITIVE LOGITS
     benefici
    0.07
    .io
    0.07
    -fe
    0.06
    _Response
    0.06
    -depth
    0.06
    -an
    0.06
    ювання
    0.06
    ])))↵
    0.06
    -products
    0.06
    .Stream
    0.06
    Act Density 0.051%

    No Known Activations