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

    Neuronpedia

    INDEX
    Explanations

    software deployment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getter
    -0.07
    Forget
    -0.06
     Casting
    -0.06
     process
    -0.06
     headaches
    -0.06
     school
    -0.06
    esson
    -0.06
     Horton
    -0.06
     suggests
    -0.06
    TCHA
    -0.06
    POSITIVE LOGITS
    (ld
    0.08
    _mux
    0.07
    Primitive
    0.06
     khẳng
    0.06
    \model
    0.06
     ediyorum
    0.06
     MaterialApp
    0.06
    _material
    0.06
    евых
    0.06
    _OVERFLOW
    0.06
    Act Density 0.031%

    No Known Activations