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
     />↵
    -0.06
     Py
    -0.06
    کت
    -0.06
     hijos
    -0.06
     explosives
    -0.06
    �
    -0.06
    ems
    -0.06
     '+'
    -0.06
    '/
    -0.06
    績
    -0.06
    POSITIVE LOGITS
     ava
    0.06
    bery
    0.06
     nếu
    0.06
     ether
    0.06
     Chaos
    0.06
    locations
    0.06
    GM
    0.06
    logout
    0.06
    ある
    0.06
     moth
    0.06
    Act Density 0.002%

    No Known Activations