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

    Neuronpedia

    INDEX
    Explanations

    bar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AST
    -0.06
    木
    -0.06
     yên
    -0.06
     descend
    -0.06
    Margin
    -0.06
     ван
    -0.06
     proposing
    -0.06
     scant
    -0.06
     dello
    -0.06
     darf
    -0.06
    POSITIVE LOGITS
     ierr
    0.09
    leaf
    0.07
    marshall
    0.07
    CLK
    0.07
    ableObject
    0.07
     proletariat
    0.07
    /↵↵↵↵
    0.06
    <>↵
    0.06
    $↵↵
    0.06
     vulnerabilities
    0.06
    Act Density 0.000%

    No Known Activations