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

    Neuronpedia

    INDEX
    Explanations

    BrainLag, opportunities, hands, branch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Тех
    0.47
    Solver
    0.44
     Тех
    0.42
     Subtle
    0.42
    ismillahirrah
    0.42
    Conservation
    0.42
    Encoder
    0.41
    Autres
    0.41
    स्पीड
    0.41
    Speed
    0.41
    POSITIVE LOGITS
     ones
    0.38
    一面
    0.38
     refuse
    0.37
     conn
    0.36
    >((
    0.36
     cheek
    0.35
     nah
    0.35
     situ
    0.34
     prepared
    0.34
     appropri
    0.34
    Act Density 0.001%

    No Known Activations