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

    Neuronpedia

    INDEX
    Explanations

    obligation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     melting
    -0.07
    .StringUtils
    -0.06
    eload
    -0.06
    sch
    -0.06
    xcb
    -0.06
    claim
    -0.06
    ากร
    -0.06
    morgan
    -0.06
    这一
    -0.06
    надлеж
    -0.06
    POSITIVE LOGITS
     GENERAL
    0.06
    iated
    0.06
     Subtract
    0.06
    NU
    0.06
    [:]↵
    0.06
     billig
    0.06
    .connect
    0.06
     ill
    0.06
     jaz
    0.06
    coli
    0.06
    Act Density 0.029%

    No Known Activations