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

    Neuronpedia

    INDEX
    Explanations

    punctuation/symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Steph
    -0.07
    efd
    -0.07
    ิต
    -0.07
    Telefone
    -0.07
     у
    -0.07
     Space
    -0.06
     лише
    -0.06
     Donetsk
    -0.06
     انتشار
    -0.06
     уг
    -0.06
    POSITIVE LOGITS
    _DISTANCE
    0.06
    Do
    0.06
     designed
    0.06
    짜
    0.06
     stating
    0.06
     procure
    0.06
     embody
    0.06
    ucha
    0.06
     harus
    0.06
     privileges
    0.06
    Act Density 0.010%

    No Known Activations