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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    職
    -0.06
     Sentry
    -0.06
    .richTextBox
    -0.06
     Hud
    -0.06
     diplom
    -0.06
     demasi
    -0.06
    .library
    -0.06
     Zus
    -0.06
     fullname
    -0.06
    .Zip
    -0.06
    POSITIVE LOGITS
     �
    0.07
     เน
    0.06
    _REV
    0.06
     aw
    0.06
     perplex
    0.06
    :result
    0.06
     사람은
    0.06
    umbledore
    0.06
    _wrapper
    0.06
    +c
    0.06
    Act Density 0.018%

    No Known Activations