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

    Neuronpedia

    INDEX
    Explanations

    pip dependency errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     «
    -0.09
    ola
    -0.09
     inc
    -0.09
    oli
    -0.09
    nic
    -0.09
    aso
    -0.09
    _
    -0.09
     Fab
    -0.09
     Glover
    -0.08
     Yup
    -0.08
    POSITIVE LOGITS
    SOR
    0.14
     sorry
    0.14
    Sorry
    0.13
     Sorry
    0.13
    sorry
    0.12
     Sor
    0.11
     sor
    0.10
    avou
    0.10
     looks
    0.10
    ÂĢÂĢ
    0.10
    Act Density 0.020%

    No Known Activations