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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Checklist
    -0.07
     Tang
    -0.07
     cornerback
    -0.06
    迹
    -0.06
    _add
    -0.06
     Resolution
    -0.06
    otope
    -0.06
     �
    -0.06
    Impro
    -0.06
    inos
    -0.06
    POSITIVE LOGITS
     spiral
    0.07
    (DialogInterface
    0.07
    ('/')[
    0.06
    VARCHAR
    0.06
     ऑनल
    0.06
     الناس
    0.06
     <--
    0.06
     Inflate
    0.06
    0.06
     سوی
    0.06
    Act Density 0.031%

    No Known Activations