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

    Neuronpedia

    INDEX
    Explanations

    Complex sentence structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Loan
    -0.06
    Safety
    -0.06
    /**<
    -0.06
     molt
    -0.06
     waiver
    -0.06
     NotImplemented
    -0.06
     benim
    -0.06
    893
    -0.05
    enames
    -0.05
    _lines
    -0.05
    POSITIVE LOGITS
    르는
    0.07
     epoch
    0.07
    ianne
    0.06
    ">$
    0.06
    >"+↵
    0.06
     integerValue
    0.06
    Linux
    0.06
     bát
    0.06
     reviews
    0.06
    ())/
    0.06
    Act Density 0.000%

    No Known Activations