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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gv
    -0.08
    ennis
    -0.07
    multip
    -0.07
     espa
    -0.07
    .Pr
    -0.07
    ,U
    -0.07
    <?↵
    -0.07
    ,v
    -0.07
    ispens
    -0.07
     espec
    -0.07
    POSITIVE LOGITS
     Ook
    0.07
    larg
    0.07
     harsh
    0.07
     regularization
    0.07
     ironic
    0.06
     LoggerFactory
    0.06
    舢
    0.06
     BrowserAnimationsModule
    0.06
    �
    0.06
    官兵
    0.06
    Act Density 0.022%

    No Known Activations