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

    Neuronpedia

    INDEX
    Explanations

    intermediate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    推进
    -0.07
     doe
    -0.07
     NOTHING
    -0.07
     suit
    -0.07
    _documento
    -0.07
    dress
    -0.07
    utton
    -0.07
     shoes
    -0.07
     dementia
    -0.07
    missing
    -0.07
    POSITIVE LOGITS
     rebuild
    0.08
    莨
    0.07
    ệm
    0.07
     }?>↵
    0.07
     TED
    0.07
    -mile
    0.07
    历程
    0.07
    ﮏ
    0.06
    Ἷ
    0.06
    乙方
    0.06
    Act Density 0.025%

    No Known Activations