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

    Neuronpedia

    INDEX
    Explanations

    scientific and technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     papeles
    0.40
    🤳
    0.37
    Референ
    0.37
     sintomi
    0.37
     kaleidos
    0.36
     emisión
    0.36
    workflows
    0.35
     NSError
    0.35
     elección
    0.35
    Eras
    0.35
    POSITIVE LOGITS
     caveat
    0.47
    odd
    0.44
    abilità
    0.40
     odd
    0.40
     giant
    0.39
     giants
    0.38
    按
    0.38
     Pants
    0.38
     apply
    0.38
     estimate
    0.38
    Act Density 0.003%

    No Known Activations