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
    .hex
    -0.07
    .Google
    -0.07
    processing
    -0.06
    green
    -0.06
    riteria
    -0.06
     Hil
    -0.06
     cloning
    -0.06
     Exposure
    -0.06
     pancakes
    -0.06
    кра
    -0.06
    POSITIVE LOGITS
    ADV
    0.06
    (T
    0.06
     sdf
    0.06
     oper
    0.06
     —
    0.06
    ando
    0.06
    _PROFILE
    0.06
     onde
    0.06
    <AM
    0.06
     davon
    0.06
    Act Density 0.040%

    No Known Activations