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

    Neuronpedia

    INDEX
    Explanations

    Version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쳔
    -0.07
    osos
    -0.07
     tắt
    -0.07
    -abortion
    -0.07
    創業
    -0.06
    _fps
    -0.06
     cio
    -0.06
    进程中
    -0.06
    מאס
    -0.06
    🥰
    -0.06
    POSITIVE LOGITS
    .Web
    0.07
    Rew
    0.07
     Silver
    0.07
    .cell
    0.07
    大气
    0.07
     Normal
    0.07
     conceal
    0.07
    rschein
    0.07
    ress
    0.07
    敌
    0.06
    Act Density 0.001%

    No Known Activations