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

    Neuronpedia

    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dart
    -0.07
     Moody
    -0.07
    nz
    -0.06
    brief
    -0.06
     twisting
    -0.06
    -yard
    -0.06
    Bru
    -0.06
     DHCP
    -0.06
    omor
    -0.06
    stri
    -0.06
    POSITIVE LOGITS
     akan
    0.06
     DETAILS
    0.06
     >>↵↵
    0.06
    禁
    0.06
    Vm
    0.06
    上げ
    0.06
     ek
    0.06
     Rails
    0.06
    shouldBe
    0.06
    ylim
    0.06
    Act Density 0.005%

    No Known Activations