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

    Neuronpedia

    INDEX
    Explanations

    technical processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     been
    -0.07
     Million
    -0.07
     were
    -0.07
     lut
    -0.06
    {l
    -0.06
     COL
    -0.06
    _BIN
    -0.06
    -million
    -0.06
     nebyl
    -0.05
     corrobor
    -0.05
    POSITIVE LOGITS
    entina
    0.07
     watering
    0.07
     etiqu
    0.07
    groupId
    0.07
     quello
    0.07
    '
↵
    0.07
    Wall
    0.07
    ض
    0.07
    Clone
    0.07
    Exiting
    0.06
    Act Density 0.236%

    No Known Activations