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

    Neuronpedia

    INDEX
    Explanations

    definition, process, cuts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Av
    0.43
    in
    0.42
    D
    0.41
    Met
    0.39
    prompt
    0.38
    Prompt
    0.38
    ische
    0.38
    ütt
    0.38
    ل
    0.37
    Interaction
    0.37
    POSITIVE LOGITS
    ብር
    0.47
     definition
    0.43
     efectivamente
    0.43
     определение
    0.42
     potted
    0.42
    ievement
    0.41
     पहुँच
    0.40
     definición
    0.40
     karar
    0.39
     definizione
    0.39
    Act Density 0.001%

    No Known Activations