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

    Neuronpedia

    INDEX
    Explanations

    1 or 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    感兴趣的
    -0.08
    🦁
    -0.08
    _fid
    -0.07
     diverse
    -0.07
     we
    -0.07
     Archae
    -0.07
    -val
    -0.07
    哿
    -0.07
    Ѡ
    -0.06
    贪婪
    -0.06
    POSITIVE LOGITS
    (writer
    0.07
     CGSizeMake
    0.07
    英国
    0.07
    (State
    0.07
    ☰
    0.07
    ลงทะ
    0.07
    	prop
    0.07
    five
    0.06
     Audit
    0.06
    thren
    0.06
    Act Density 0.000%

    No Known Activations