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

    Neuronpedia

    INDEX
    Explanations

    technical or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لو
    0.32
    urut
    0.31
     ay
    0.30
     Gal
    0.30
     Onda
    0.29
     gdje
    0.29
     disappeared
    0.29
    ly
    0.29
    ard
    0.29
     oranges
    0.29
    POSITIVE LOGITS
    ਾਨੂੰ
    0.37
    第一題
    0.36
    題目
    0.35
    PipelineState
    0.35
     peneliti
    0.35
     паци
    0.35
    Genetic
    0.34
    Prototype
    0.34
    Ligações
    0.34
     హై
    0.33
    Act Density 0.000%

    No Known Activations