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
    Unicode
    -0.09
     razor
    -0.07
    ')↵↵
    -0.07
    潟
    -0.07
     cú
    -0.07
    monitor
    -0.06
    ☄
    -0.06
    ts
    -0.06
    的核心
    -0.06
    חום
    -0.06
    POSITIVE LOGITS
     '**
    0.07
     embroid
    0.07
     persec
    0.07
    belie
    0.07
    VERRIDE
    0.07
    _consum
    0.07
     *,
    0.07
    myModal
    0.06
     referral
    0.06
    ="'
    0.06
    Act Density 0.000%

    No Known Activations