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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lox
    -0.07
    que
    -0.07
     FORMAT
    -0.07
    aco
    -0.07
     atoi
    -0.07
     chin
    -0.07
     Cox
    -0.06
    <Vector
    -0.06
     component
    -0.06
     Loc
    -0.06
    POSITIVE LOGITS
    7
    0.09
    197
    0.09
    127
    0.08
    ७
    0.08
     seven
    0.07
    47
    0.07
    827
    0.07
    117
    0.07
     Seven
    0.07
    177
    0.07
    Act Density 0.275%

    No Known Activations