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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ig
    -0.08
     sput
    -0.08
    Ig
    -0.08
     zusamm
    -0.07
    厚
    -0.07
     dunkel
    -0.07
     ae
    -0.07
     मू
    -0.07
    টির
    -0.07
     Ат
    -0.07
    POSITIVE LOGITS
    FP
    0.08
    DP
    0.08
    0.08
    拟
    0.08
     자연
    0.08
     شهد
    0.08
    (cpu
    0.07
     atao
    0.07
    clar
    0.07
    Have
    0.07
    Act Density 0.337%
    No Known Activations