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

    Neuronpedia

    INDEX
    Explanations

    sp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     título
    -0.07
    Fu
    -0.07
     Mun
    -0.07
    opot
    -0.06
     woll
    -0.06
     criticised
    -0.06
     Ol
    -0.06
     Corpus
    -0.06
     childish
    -0.06
     strikes
    -0.06
    POSITIVE LOGITS
    instrument
    0.07
    患者
    0.06
    .src
    0.06
    ective
    0.06
     peny
    0.06
     panor
    0.06
    าผ
    0.06
    .Engine
    0.06
    defgroup
    0.06
    πουλος
    0.06
    Act Density 0.002%

    No Known Activations