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

    Neuronpedia

    INDEX
    Explanations

    Dolphins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mereka
    -0.98
     Mereka
    -0.86
    Their
    -0.84
    mereka
    -0.81
     them
    -0.80
    their
    -0.80
     mereka
    -0.79
     They
    -0.79
     Their
    -0.79
     ihnen
    -0.79
    POSITIVE LOGITS
     оно
    0.44
    utnik
    0.42
     it
    0.41
    allergenic
    0.41
     sözler
    0.41
    openSession
    0.39
     It
    0.38
     juridique
    0.38
    isDebugEnabled
    0.36
     olvides
    0.36
    Act Density 0.005%

    No Known Activations