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

    Neuronpedia

    INDEX
    Explanations

    can/will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    strconv
    -0.07
    .permission
    -0.07
    escaping
    -0.06
     statically
    -0.06
     LaTeX
    -0.06
     thriller
    -0.06
    ANTE
    -0.06
    рев
    -0.06
     funct
    -0.06
     yapılması
    -0.06
    POSITIVE LOGITS
    =S
    0.07
     Stall
    0.07
     самостоятельно
    0.07
    “All
    0.07
     세계
    0.06
     Cynthia
    0.06
    .get
    0.06
     Cube
    0.06
     Roof
    0.06
    =X
    0.06
    Act Density 0.044%

    No Known Activations