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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bonded
    -0.07
    Builders
    -0.07
    ущ
    -0.07
     После
    -0.07
    「え
    -0.07
     Responsibility
    -0.07
     knot
    -0.06
     skiing
    -0.06
    _r
    -0.06
     помогает
    -0.06
    POSITIVE LOGITS
    trecht
    0.07
    inosaur
    0.06
    frica
    0.06
    美
    0.06
    Via
    0.06
     Aad
    0.06
    ablo
    0.06
     dictionaries
    0.06
    리아
    0.06
    lesia
    0.06
    Act Density 0.004%

    No Known Activations