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

    Neuronpedia

    INDEX
    Explanations

    assistance, guarantees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infatti
    -0.09
     Landscaping
    -0.09
     Mineral
    -0.08
     Mig
    -0.08
    ask
    -0.08
    enes
    -0.08
     Capitol
    -0.08
    vek
    -0.08
     revis
    -0.08
     Preg
    -0.07
    POSITIVE LOGITS
     ולה
    0.11
     ול
    0.11
    ्टी
    0.07
     möglichst
    0.07
     tro
    0.07
    Punch
    0.07
     उम
    0.07
     बनाया
    0.07
     сверх
    0.07
     sole
    0.07
    Act Density 0.316%

    No Known Activations