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

    Neuronpedia

    INDEX
    Explanations

    false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Burb
    -0.07
    Trip
    -0.07
    tabl
    -0.06
     top
    -0.06
    Top
    -0.06
     paginator
    -0.06
     Top
    -0.06
    .wp
    -0.06
     Naughty
    -0.06
     YY
    -0.06
    POSITIVE LOGITS
     false
    0.12
    false
    0.10
    False
    0.10
     False
    0.10
    _failure
    0.08
     FALSE
    0.08
    故
    0.08
    direction
    0.08
    =False
    0.07
    iste
    0.07
    Act Density 0.019%

    No Known Activations