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

    Neuronpedia

    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pipe
    -0.07
     afs
    -0.07
    lus
    -0.07
    	sig
    -0.07
    _HE
    -0.07
     generous
    -0.06
    旁边的
    -0.06
     trợ
    -0.06
     gorge
    -0.06
     organs
    -0.06
    POSITIVE LOGITS
    ●
    0.07
     retali
    0.07
    �
    0.07
     broadcast
    0.07
    TION
    0.07
    .Batch
    0.07
    داء
    0.07
    Editor
    0.07
    终生
    0.07
    برا
    0.07
    Act Density 0.040%

    No Known Activations