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

    Neuronpedia

    INDEX
    Explanations

    options and scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assolutamente
    0.52
     réellement
    0.50
     столь
    0.50
     extremamente
    0.49
     انتہائی
    0.49
     completamente
    0.49
     únicamente
    0.49
     extrêmement
    0.49
     تمامی
    0.49
     equipamento
    0.48
    POSITIVE LOGITS
     diversify
    0.46
     diversified
    0.43
     reusing
    0.37
     kreativ
    0.36
     mostly
    0.36
     diversification
    0.36
     creatividad
    0.35
     richness
    0.35
     cooperate
    0.34
     reuse
    0.34
    Act Density 0.010%

    No Known Activations