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

    Neuronpedia

    INDEX
    Explanations

    qualified healthcare professional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cellent
    0.42
    ibrated
    0.41
     Regione
    0.40
    鲸
    0.39
    牦
    0.38
     kualitas
    0.38
    وسیع
    0.38
     හො
    0.38
    rectionType
    0.38
    ၺ
    0.37
    POSITIVE LOGITS
    ትር
    0.39
    listener
    0.39
     tips
    0.37
     medical
    0.37
     health
    0.36
     user
    0.35
     somatic
    0.35
    pring
    0.35
     hate
    0.35
     actions
    0.34
    Act Density 0.001%

    No Known Activations