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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    รม
    -0.07
    _qty
    -0.07
     hatta
    -0.07
     useSelector
    -0.07
     hott
    -0.06
    .rnn
    -0.06
     Intelligence
    -0.06
     gotten
    -0.06
     rotating
    -0.06
    detach
    -0.06
    POSITIVE LOGITS
    bid
    0.07
    .Info
    0.07
    -sk
    0.07
     PHI
    0.06
    那些
    0.06
    -authored
    0.06
    charged
    0.06
    gl
    0.06
    (fd
    0.06
    _prot
    0.06
    Act Density 0.007%

    No Known Activations