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

    Neuronpedia

    INDEX
    Explanations

    assume

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    乏
    -0.08
    Array
    -0.07
     suffice
    -0.07
    دق
    -0.07
    之举
    -0.06
    莹
    -0.06
    ce
    -0.06
    دة
    -0.06
     BaseType
    -0.06
    纫
    -0.06
    POSITIVE LOGITS
    エネルギー
    0.08
     accessibility
    0.07
     pressure
    0.07
     ост
    0.07
     compressed
    0.07
     proposal
    0.07
     사람이
    0.07
    .ser
    0.07
    設計
    0.07
    一声
    0.06
    Act Density 0.020%

    No Known Activations