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

    Neuronpedia

    INDEX
    Explanations

    code syntax and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nadores
    -1.10
     produtos
    -1.05
     viernes
    -1.00
     gebruiken
    -0.99
    umme
    -0.97
     león
    -0.94
     miłości
    -0.92
     producten
    -0.91
    klinik
    -0.90
    oa̍t
    -0.90
    POSITIVE LOGITS
     exchanged
    0.98
     zufolge
    0.96
    ->___
    0.90
     upro
    0.84
     forcibly
    0.82
     Relocation
    0.82
     exchanging
    0.82
     when
    0.82
     correction
    0.80
    ostoma
    0.79
    Act Density 0.001%

    No Known Activations