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

    Neuronpedia

    INDEX
    Explanations

    AR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    checkout
    -0.07
    콜걸
    -0.07
    _children
    -0.06
    Needs
    -0.06
    470
    -0.06
     परम
    -0.06
    (light
    -0.06
    [vi
    -0.06
    outine
    -0.05
    (place
    -0.05
    POSITIVE LOGITS
    RAR
    0.18
     rar
    0.13
    rar
    0.13
    AR
    0.10
    .rar
    0.10
    ar
    0.09
    ror
    0.09
     Rory
    0.09
    ARA
    0.09
    LAR
    0.08
    Act Density 0.003%

    No Known Activations