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

    Neuronpedia

    INDEX
    Explanations

    Mac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onAttach
    -0.50
    таратура
    -0.49
    ğum
    -0.48
    aspectj
    -0.48
    addLast
    -0.46
    Hướng
    -0.45
    hythm
    -0.45
    cienti
    -0.44
    Personajes
    -0.44
     reward
    -0.43
    POSITIVE LOGITS
    PYX
    0.65
    fjspx
    0.63
     "..\..\
    0.57
    PhysRev
    0.57
    >{@
    0.57
    ViewImports
    0.55
     gynhyrchwyd
    0.52
     &___
    0.52
    SuccessListener
    0.50
    NameInMap
    0.49
    Act Density 0.002%

    No Known Activations