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

    Neuronpedia

    INDEX
    Explanations

    bar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     layer
    -0.07
     Sense
    -0.07
    Impossible
    -0.07
     sidelines
    -0.07
     giant
    -0.07
     Hopefully
    -0.06
     rescued
    -0.06
    imu
    -0.06
     Loud
    -0.06
     kwargs
    -0.06
    POSITIVE LOGITS
    ’deki
    0.06
    ập
    0.06
     Registr
    0.06
    ccb
    0.06
     ".$
    0.06
    цип
    0.06
    __":↵
    0.06
     escri
    0.06
     método
    0.06
    "></
    0.06
    Act Density 0.010%

    No Known Activations