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

    Neuronpedia

    INDEX
    Explanations

    pedestrian anatomy kg day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    totalSupply
    0.54
    atmosphère
    0.48
    MktCap
    0.48
    만을
    0.46
    ༨
    0.45
     monopol
    0.45
    Austral
    0.44
    itsar
    0.44
    PatientR
    0.44
    ousands
    0.44
    POSITIVE LOGITS
     diventa
    0.47
     reversing
    0.46
     Seems
    0.45
     Writes
    0.45
     Different
    0.45
     lr
    0.43
     Driving
    0.42
     adding
    0.42
     correctement
    0.42
     selon
    0.42
    Act Density 0.003%

    No Known Activations