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

    Neuronpedia

    INDEX
    Explanations

    steady

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     telefone
    -0.08
    ancouver
    -0.07
    แปลง
    -0.07
     철
    -0.07
    -rel
    -0.07
     органі
    -0.07
     interfaces
    -0.07
     発
    -0.07
    CPF
    -0.07
     evrop
    -0.07
    POSITIVE LOGITS
     steady
    0.21
     steadily
    0.13
    steady
    0.11
     stead
    0.08
     stacks
    0.07
     steadfast
    0.07
     advised
    0.07
    75
    0.06
    /comments
    0.06
     Shan
    0.06
    Act Density 0.002%

    No Known Activations