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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     에
    -0.08
     itching
    -0.08
    unities
    -0.07
     lake
    -0.07
     pots
    -0.06
     trolling
    -0.06
     後
    -0.06
    �数
    -0.06
    Iterations
    -0.06
    лев
    -0.06
    POSITIVE LOGITS
     <!
    0.07
    -largest
    0.06
    918
    0.06
    )`
    0.06
     Valencia
    0.06
    \Json
    0.06
     Roberto
    0.06
     лі
    0.06
    Þ
    0.06
     Ibrahim
    0.06
    Act Density 0.041%

    No Known Activations