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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Evrop
    -0.07
    ापक
    -0.07
     milyar
    -0.06
    udoku
    -0.06
     삶
    -0.06
    avn
    -0.06
     hele
    -0.06
     Blackburn
    -0.06
     imgUrl
    -0.06
     nastav
    -0.06
    POSITIVE LOGITS
     aut
    0.07
    五
    0.07
    防
    0.06
    /auth
    0.06
    SAT
    0.06
     Cons
    0.06
     append
    0.06
     SHA
    0.06
     cop
    0.06
     alph
    0.06
    Act Density 0.005%

    No Known Activations