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

    Neuronpedia

    INDEX
    Explanations

    qualities and defects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кция
    0.49
    кции
    0.46
     Т
    0.45
     Jaan
    0.45
    阃
    0.44
     alterar
    0.43
     almacenamiento
    0.43
    演
    0.42
     К
    0.42
     எஸ்
    0.42
    POSITIVE LOGITS
    surprise
    0.50
    full
    0.48
    ishly
    0.45
     exaggerated
    0.43
    damn
    0.42
     exager
    0.41
     glowing
    0.41
    good
    0.41
     dreamy
    0.40
     outrageous
    0.40
    Act Density 0.001%

    No Known Activations