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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WND
    -0.07
    emale
    -0.07
    Views
    -0.07
    .available
    -0.07
    CEL
    -0.07
    Stand
    -0.07
    BAD
    -0.07
    sequent
    -0.07
    cludes
    -0.07
    漏洞
    -0.07
    POSITIVE LOGITS
    핱
    0.08
    冲刺
    0.07
     revert
    0.07
    طف
    0.07
     נשמע
    0.07
    珒
    0.07
    を目
    0.07
     перед
    0.07
    暝
    0.07
    裁员
    0.07
    Act Density 0.041%

    No Known Activations