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

    Neuronpedia

    INDEX
    Explanations

    data loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leyen
    -0.07
     Scotia
    -0.07
     Rachel
    -0.06
    LA
    -0.06
    Gene
    -0.06
    อค
    -0.06
    ось
    -0.06
    kus
    -0.06
     deutschland
    -0.06
    斯
    -0.06
    POSITIVE LOGITS
     sinon
    0.06
    xf
    0.06
     Girlfriend
    0.06
     madd
    0.06
     Leave
    0.06
     Gig
    0.06
     UserName
    0.06
    periment
    0.06
    oader
    0.06
    确
    0.06
    Act Density 0.036%

    No Known Activations