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

    Neuronpedia

    INDEX
    Explanations

    imated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :flex
    -0.06
    antlr
    -0.06
    operation
    -0.06
     frantic
    -0.06
     �
    -0.06
    。これ
    -0.05
     footnote
    -0.05
     rationale
    -0.05
     legalization
    -0.05
     proponents
    -0.05
    POSITIVE LOGITS
     celebrity
    0.07
    `(
    0.07
    (),'
    0.07
     comforting
    0.07
    Hours
    0.07
     calming
    0.07
     mail
    0.07
    >@
    0.06
    CONST
    0.06
     mailed
    0.06
    Act Density 0.002%

    No Known Activations