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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Diwedd
    -0.54
    Попис
    -0.53
    قایناقلار
    -0.52
    équi
    -0.51
     geholfen
    -0.50
    ABAJO
    -0.50
    ſelves
    -0.50
    CompleteListener
    -0.50
     старости
    -0.50
    waitKey
    -0.49
    POSITIVE LOGITS
     Meksiku
    0.47
     Olson
    0.46
     ©️
    0.45
    ciso
    0.45
     leg
    0.44
     goda
    0.44
     Stevenson
    0.44
     MOON
    0.43
    akhstan
    0.43
     intelligence
    0.43
    Act Density 0.001%

    No Known Activations