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

    Neuronpedia

    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adviser
    -0.07
    onders
    -0.07
    TEGR
    -0.06
     Leopard
    -0.06
     along
    -0.06
     Owners
    -0.06
     spouse
    -0.06
    ocial
    -0.06
     reinforce
    -0.06
    .it
    -0.06
    POSITIVE LOGITS
     wy
    0.07
     out
    0.07
     ousted
    0.07
     вып
    0.07
     выб
    0.07
     вывод
    0.07
    .shortcuts
    0.07
     heraus
    0.06
     выступ
    0.06
     بیرون
    0.06
    Act Density 0.031%

    No Known Activations