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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pv
    -0.07
     is
    -0.06
    Tap
    -0.06
    LObject
    -0.06
    692
    -0.06
     fanc
    -0.06
     Mosul
    -0.06
     my
    -0.06
    Three
    -0.06
    Ê
    -0.06
    POSITIVE LOGITS
     SLOT
    0.07
     to
    0.07
     gắng
    0.06
     alike
    0.06
     Transmit
    0.06
     року
    0.06
     Bảo
    0.06
    -Allow
    0.06
    /comments
    0.06
    未
    0.06
    Act Density 0.044%

    No Known Activations