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

    Neuronpedia

    INDEX
    Explanations

    html code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nid
    0.58
     Examiners
    0.57
     Gone
    0.57
     checking
    0.56
     Checking
    0.55
     querying
    0.54
     Written
    0.54
     contoured
    0.53
    iracial
    0.53
     Cause
    0.53
    POSITIVE LOGITS
    ><
    0.89
     receta
    0.75
    Yvette
    0.70
     preferencias
    0.69
     flera
    0.67
     complicaciones
    0.64
     particularmente
    0.62
     compacto
    0.62
     பாம்பு
    0.62
     viele
    0.62
    Act Density 0.017%

    No Known Activations