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

    Neuronpedia

    INDEX
    Explanations

    Parentheses/brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (U
    -0.07
    _third
    -0.07
     removal
    -0.07
    ax
    -0.06
    -u
    -0.06
     人
    -0.06
    amar
    -0.06
     sonu
    -0.06
     Way
    -0.06
    pu
    -0.06
    POSITIVE LOGITS
    标准
    0.07
    认识
    0.07
    _hz
    0.07
     DXGI
    0.06
     holster
    0.06
    терн
    0.06
    ]=>
    0.06
    ());//
    0.06
     confirmPassword
    0.06
     presently
    0.06
    Act Density 0.025%

    No Known Activations