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

    Neuronpedia

    INDEX
    Explanations

    yr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    days
    -0.87
    mann
    -0.81
    yr
    -0.72
    MANN
    -0.63
    ya
    -0.58
    yrs
    -0.54
     Their
    -0.53
    kali
    -0.53
     мәкал
    -0.53
     Its
    -0.53
    POSITIVE LOGITS
    ISupport
    0.54
    :]:
    0.51
     iconFacebook
    0.51
    LETED
    0.50
    TRAILING
    0.50
     aDecoder
    0.50
    hbase
    0.49
    !*\
    0.49
    SBATCH
    0.49
    ussis
    0.48
    Act Density 0.059%

    No Known Activations