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

    Neuronpedia

    INDEX
    Explanations

    story

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nó
    -0.07
    .mime
    -0.07
    	attack
    -0.06
    trigger
    -0.06
    igital
    -0.06
     Nico
    -0.06
     goal
    -0.06
    둥
    -0.06
    -0.06
    spa
    -0.06
    POSITIVE LOGITS
    中华
    0.07
     дерев
    0.07
    vendors
    0.07
     "'.$
    0.06
     зберіг
    0.06
     分
    0.06
     هزینه
    0.06
     조선
    0.06
     viv
    0.06
    ounds
    0.06
    Act Density 0.017%

    No Known Activations