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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    自贸
    -0.08
     nicer
    -0.07
    ᎒
    -0.07
     작
    -0.07
    omore
    -0.06
    ווא
    -0.06
     ndarray
    -0.06
    どういう
    -0.06
    ptions
    -0.06
    浮
    -0.06
    POSITIVE LOGITS
    ropol
    0.07
    银河
    0.07
    🔀
    0.06
     Dante
    0.06
    _collect
    0.06
     Negro
    0.06
    赌
    0.06
    Mus
    0.06
    世界上最
    0.06
     notebooks
    0.06
    Act Density 0.048%

    No Known Activations