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

    Neuronpedia

    INDEX
    Explanations

    Resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’autres
    -0.07
     distort
    -0.07
     Podle
    -0.07
     peux
    -0.06
     bez
    -0.06
    ANCES
    -0.06
    Healthy
    -0.06
     Kra
    -0.06
     sam
    -0.06
     seal
    -0.06
    POSITIVE LOGITS
     disposit
    0.07
     сколько
    0.07
     intervened
    0.06
    _ret
    0.06
    ولات
    0.06
     migrate
    0.06
     اتفاق
    0.06
    retch
    0.06
     〈
    0.06
     MM
    0.06
    Act Density 0.000%

    No Known Activations