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

    Neuronpedia

    INDEX
    Explanations

    allocation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    드리
    -0.07
    ンチ
    -0.07
    Вы
    -0.06
     Blockchain
    -0.06
    orpor
    -0.06
     cliffs
    -0.06
     वस
    -0.06
    ，便
    -0.06
    ()].
    -0.06
    strong
    -0.06
    POSITIVE LOGITS
     nomination
    0.08
    junction
    0.06
     Practices
    0.06
     lorsque
    0.06
     intellectual
    0.06
     enlightenment
    0.06
     teachings
    0.06
     Restart
    0.06
    Dual
    0.06
     entries
    0.06
    Act Density 0.015%

    No Known Activations