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

    Neuronpedia

    INDEX
    Explanations

    sections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -caret
    -0.07
     نیاز
    -0.07
     supp
    -0.07
    添
    -0.07
     mate
    -0.07
     عباس
    -0.07
     flaming
    -0.07
    ΟΙ
    -0.07
    _username
    -0.06
     SEG
    -0.06
    POSITIVE LOGITS
    끔
    0.07
    -region
    0.06
    чук
    0.06
    IDGET
    0.06
     Recording
    0.06
    Screens
    0.06
    lz
    0.06
    غط
    0.06
    atholic
    0.06
    cheid
    0.06
    Act Density 0.001%

    No Known Activations