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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Get
    -0.07
    (ep
    -0.07
    .species
    -0.07
     �
    -0.07
     Enable
    -0.07
    	Token
    -0.07
     CDDL
    -0.07
     collagen
    -0.07
     chrome
    -0.07
     som
    -0.06
    POSITIVE LOGITS
    VAS
    0.06
    enta
    0.06
     nuôi
    0.06
     cải
    0.06
    buquerque
    0.06
    握
    0.06
    mi
    0.06
    몰
    0.06
    (fmt
    0.06
     ztr
    0.05
    Act Density 0.116%

    No Known Activations