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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exploding
    -0.08
    ervention
    -0.07
     lame
    -0.07
     Pill
    -0.06
     microscopic
    -0.06
     editions
    -0.06
     abrupt
    -0.06
     doe
    -0.06
     tweets
    -0.06
     primitive
    -0.06
    POSITIVE LOGITS
    CALE
    0.07
    不断扩大
    0.07
     Aircraft
    0.07
    方向盘
    0.07
    hte
    0.06
    选�
    0.06
    (dst
    0.06
    ナイ
    0.06
    enh
    0.06
    :animated
    0.06
    Act Density 0.010%

    No Known Activations