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

    Neuronpedia

    INDEX
    Explanations

    comparisons of size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ีเด
    -0.07
     oldukları
    -0.07
    라마
    -0.06
    nk
    -0.06
     LIN
    -0.06
     reshape
    -0.06
    friends
    -0.06
    Subviews
    -0.06
    quis
    -0.06
    >N
    -0.06
    POSITIVE LOGITS
    웃
    0.07
     mlad
    0.07
    ुजर
    0.07
     hijo
    0.07
     घटन
    0.06
     honest
    0.06
     Occ
    0.06
     Mesa
    0.06
     Každ
    0.06
     Miles
    0.06
    Act Density 0.017%

    No Known Activations