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

    Neuronpedia

    INDEX
    Explanations

    rougher and harder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     matéri
    0.52
     gare
    0.51
     gió
    0.50
     âge
    0.50
     facil
    0.50
     aşağı
    0.49
     épaisse
    0.48
     acesso
    0.47
     facile
    0.46
     êtres
    0.46
    POSITIVE LOGITS
    ד
    0.54
     தெரிவித்த
    0.51
     Первый
    0.49
     Solvent
    0.48
     ሥራ
    0.47
     Superf
    0.46
    enn
    0.46
    ល់
    0.45
    ill
    0.44
     ली
    0.44
    Act Density 0.000%

    No Known Activations