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

    Neuronpedia

    INDEX
    Explanations

    servers | industry | encrypt | 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uğu
    0.44
    uğ
    0.44
     politics
    0.41
     проблема
    0.40
    arl
    0.39
     орган
    0.39
     против
    0.38
    allas
    0.38
    ací
    0.38
    ະພັນ
    0.38
    POSITIVE LOGITS
     grosso
    0.50
     poner
    0.48
     Poche
    0.46
     rueda
    0.46
     sentido
    0.46
     centrif
    0.46
     captura
    0.46
     brighten
    0.46
     entsprechenden
    0.45
     اثنين
    0.45
    Act Density 0.002%

    No Known Activations