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

    Neuronpedia

    INDEX
    Explanations

    Chemical compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Quest
    -0.07
    赵
    -0.07
     ChatColor
    -0.06
    步
    -0.06
    币
    -0.06
    038
    -0.06
     vulnerabilities
    -0.06
     ($("#
    -0.06
     fetish
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    practice
    0.06
    .Authentication
    0.06
    ateg
    0.06
     stringWith
    0.06
     #"
    0.06
    Wrong
    0.06
     horizontally
    0.06
     suspension
    0.06
    	reset
    0.06
    atal
    0.06
    Act Density 0.006%

    No Known Activations