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

    Neuronpedia

    INDEX
    Explanations

    concrete

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zug
    -0.07
     allem
    -0.07
    /N
    -0.07
     giant
    -0.07
    .ne
    -0.06
     اين
    -0.06
    iera
    -0.06
    claim
    -0.06
     fees
    -0.06
     trains
    -0.06
    POSITIVE LOGITS
    ड़क
    0.07
     FactoryGirl
    0.06
    !↵↵↵
    0.06
     ]]↵
    0.06
    Gene
    0.06
     vysvět
    0.06
    ComputedStyle
    0.06
     představ
    0.06
    xfff
    0.06
     Микола
    0.06
    Act Density 0.003%

    No Known Activations