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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CONTROLLER
    -0.07
     darüber
    -0.07
    _throw
    -0.06
    ۴۰
    -0.06
     eigen
    -0.06
    .partial
    -0.06
     cảnh
    -0.06
     interrupt
    -0.06
     pops
    -0.06
     bitcoin
    -0.06
    POSITIVE LOGITS
    -made
    0.06
    writer
    0.06
     Mehmet
    0.06
    _means
    0.06
    yc
    0.06
    -fin
    0.06
    _vlog
    0.06
    しない
    0.05
    협
    0.05
     programmed
    0.05
    Act Density 0.128%

    No Known Activations