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

    Neuronpedia

    INDEX
    Explanations

    provide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Conv
    -0.07
     XOR
    -0.07
     уже
    -0.07
    RACT
    -0.07
    _certificate
    -0.07
     키
    -0.06
    conv
    -0.06
     volont
    -0.06
     algorithms
    -0.06
    ampionship
    -0.06
    POSITIVE LOGITS
     outra
    0.07
     dost
    0.07
     WebElement
    0.07
     {{
    0.06
     giving
    0.06
    注
    0.06
     e
    0.06
    12
    0.06
     inspector
    0.06
     intest
    0.06
    Act Density 0.035%

    No Known Activations