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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     möglichst
    -0.10
     undesirable
    -0.08
    പ്പെട
    -0.08
     dichos
    -0.08
     తద
    -0.08
     diens
    -0.08
    不得
    -0.08
     moeten
    -0.08
     unten
    -0.07
     অথবা
    -0.07
    POSITIVE LOGITS
     infatti
    0.10
     vya
    0.09
    Equation
    0.08
     Në
    0.08
     Finch
    0.08
    āc
    0.08
     structur
    0.08
     totiž
    0.08
     namelijk
    0.08
    ugi
    0.08
    Act Density 0.116%

    No Known Activations