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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plupart
    0.43
     Scarborough
    0.41
     Believe
    0.41
     Prima
    0.40
     Lockwood
    0.39
     Canal
    0.39
     Judy
    0.38
     Reynolds
    0.38
     Marlene
    0.38
     name
    0.37
    POSITIVE LOGITS
    ເຊ
    0.50
     biogas
    0.49
     plabic
    0.49
     pacient
    0.47
     favorables
    0.47
     celular
    0.46
    ப்பும்
    0.46
    ценка
    0.46
     estud
    0.45
     अध्य
    0.44
    Act Density 0.009%

    No Known Activations