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

    Neuronpedia

    INDEX
    Explanations

    Lengthy, rambling texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    들과
    -0.07
     شوند
    -0.06
    她的
    -0.06
     معماری
    -0.06
     pessoas
    -0.06
    _REFER
    -0.06
    ภาคม
    -0.06
     bý
    -0.06
    anlı
    -0.06
    _cross
    -0.06
    POSITIVE LOGITS
     inference
    0.06
    ог
    0.06
     egg
    0.06
    �
    0.06
    091
    0.06
     injecting
    0.06
     Дж
    0.06
    _GE
    0.06
     정신
    0.06
    Gi
    0.06
    Act Density 0.000%

    No Known Activations