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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hra
    -0.08
    人员
    -0.07
     wagon
    -0.07
     želez
    -0.06
     Newsp
    -0.06
    pitch
    -0.06
    ERO
    -0.06
    bounds
    -0.06
    omo
    -0.06
    EndInit
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    parity
    0.06
    olves
    0.06
     چیست
    0.06
     kred
    0.06
     ={↵
    0.06
    =http
    0.06
    /controller
    0.06
    itational
    0.06
     М
    0.06
    Act Density 0.131%

    No Known Activations