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

    Neuronpedia

    INDEX
    Explanations

    Making a choice, sticking with it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Monday
    -0.07
     battlefield
    -0.07
     comment
    -0.07
     distressed
    -0.06
     Ear
    -0.06
     god
    -0.06
    domain
    -0.06
    Lookup
    -0.06
     bear
    -0.06
     beer
    -0.06
    POSITIVE LOGITS
    elder
    0.07
    .XR
    0.07
    uzey
    0.06
    ิกา
    0.06
    Regs
    0.06
     nejsou
    0.06
     생활
    0.06
     امتی
    0.06
     اروپ
    0.06
    setVisible
    0.06
    Act Density 0.087%

    No Known Activations