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

    Neuronpedia

    INDEX
    Explanations

    firsts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propio
    -0.06
    .Alpha
    -0.06
    [level
    -0.06
    InteractionEnabled
    -0.06
     lingering
    -0.06
     conflic
    -0.06
     egregious
    -0.06
    	level
    -0.06
    .bam
    -0.06
     Only
    -0.06
    POSITIVE LOGITS
    WithTitle
    0.07
    toggleClass
    0.07
    (pk
    0.07
                            ↵
    0.07
     دلار
    0.06
     Merchant
    0.06
    ۱۹۷
    0.06
    Published
    0.06
     updateUser
    0.06
    億
    0.06
    Act Density 0.091%

    No Known Activations