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

    Neuronpedia

    INDEX
    Explanations

    legal/formal texts fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tract
    -0.06
    igner
    -0.06
    Whenever
    -0.06
     weblog
    -0.06
    Modal
    -0.06
     ayuda
    -0.06
    .gallery
    -0.06
     JNI
    -0.06
    trusted
    -0.06
    Else
    -0.06
    POSITIVE LOGITS
    _codigo
    0.06
    inance
    0.06
     datasets
    0.06
     серед
    0.06
    _EOF
    0.06
    -dem
    0.06
    .Entity
    0.06
    .Deep
    0.06
    .modelo
    0.06
     syscall
    0.06
    Act Density 0.017%

    No Known Activations