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

    Neuronpedia

    INDEX
    Explanations

    dirty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EATURE
    -0.06
    👸
    -0.06
     compulsory
    -0.06
    ⏯
    -0.06
    //↵↵
    -0.06
    %)↵↵
    -0.06
     Thu
    -0.06
    score
    -0.06
    拼多多
    -0.06
    畔
    -0.06
    POSITIVE LOGITS
     det
    0.08
     dirty
    0.08
     diret
    0.08
    -cat
    0.07
    DetailView
    0.07
     Dirty
    0.07
    Dirty
    0.07
     dire
    0.07
    ادات
    0.07
    acion
    0.07
    Act Density 0.005%

    No Known Activations