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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breaks
    -0.07
     Moderate
    -0.06
     kur
    -0.06
    луч
    -0.06
     marshaller
    -0.06
    _REGS
    -0.06
     lesbian
    -0.06
     servers
    -0.06
    Chip
    -0.06
     TouchableOpacity
    -0.06
    POSITIVE LOGITS
    ='.$
    0.07
    DSP
    0.07
    _TRACE
    0.06
    олом
    0.06
     ►
    0.06
     decades
    0.06
     checkout
    0.06
     _____
    0.06
    -before
    0.06
    .robot
    0.06
    Act Density 0.161%

    No Known Activations