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

    Neuronpedia

    INDEX
    Explanations

    alternatives to cars

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    协助
    -0.07
    //}↵↵
    -0.07
    ]<=
    -0.06
     weak
    -0.06
     understandably
    -0.06
    減少
    -0.06
    [offset
    -0.06
     week
    -0.06
     _)
    -0.06
    ◣
    -0.06
    POSITIVE LOGITS
    ilde
    0.07
    撒
    0.07
    กรรม
    0.07
     TMP
    0.07
    掷
    0.07
     Json
    0.06
     cleanse
    0.06
    直线
    0.06
    FS
    0.06
    爵士
    0.06
    Act Density 0.069%

    No Known Activations