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

    Neuronpedia

    INDEX
    Explanations

    make sure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Detach
    0.77
     புகழ்
    0.77
    amanya
    0.76
    ništva
    0.75
    acijos
    0.74
     ehemal
    0.74
     निजात
    0.74
    мулятор
    0.74
    aderie
    0.72
    CheckingType
    0.72
    POSITIVE LOGITS
     sure
    2.31
     sense
    1.68
     amends
    1.67
     inroads
    1.61
    sure
    1.50
     headway
    1.49
     Sure
    1.43
     adjustments
    1.41
     decisions
    1.38
     SURE
    1.36
    Act Density 0.171%

    No Known Activations