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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dtp
    -0.08
    调剂
    -0.07
    ➽
    -0.06
    ashboard
    -0.06
    _spinner
    -0.06
    也不知道
    -0.06
     במיד
    -0.06
    แดด
    -0.06
    .It
    -0.06
    享受到
    -0.06
    POSITIVE LOGITS
    大发
    0.07
     REV
    0.07
    clamation
    0.07
     Schwarz
    0.07
     manipulated
    0.06
    (RE
    0.06
     swallowed
    0.06
     ludicrous
    0.06
    (Expected
    0.06
     Fatal
    0.06
    Act Density 0.006%

    No Known Activations