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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tection
    -0.07
    Sequential
    -0.07
    .damage
    -0.07
    coholic
    -0.07
     khá
    -0.07
    <<"
    -0.07
     ges
    -0.06
    selector
    -0.06
     limited
    -0.06
    ra
    -0.06
    POSITIVE LOGITS
     itir
    0.06
     Cly
    0.06
     ASN
    0.06
     Highest
    0.06
     lys
    0.05
    -lived
    0.05
    烦
    0.05
     Irene
    0.05
     useClass
    0.05
     messy
    0.05
    Act Density 0.000%

    No Known Activations