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

    Neuronpedia

    INDEX
    Explanations

    per unit or geographic area

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caff
    0.43
     замести
    0.39
    Ꮃ
    0.39
     gabb
    0.38
     Riva
    0.37
     caud
    0.37
     afiliados
    0.37
     విశ్వ
    0.36
     infra
    0.36
     frameworks
    0.36
    POSITIVE LOGITS
     UNIT
    0.43
    Unit
    0.42
     Unit
    0.42
    iunea
    0.41
     unit
    0.41
    unit
    0.40
    ic
    0.38
    ics
    0.38
    ovable
    0.38
    北大
    0.38
    Act Density 0.000%

    No Known Activations