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

    Neuronpedia

    INDEX
    Explanations

    column

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     initiator
    -0.07
     Dos
    -0.06
     crossings
    -0.06
     parchment
    -0.06
     корол
    -0.06
     functions
    -0.06
     Household
    -0.06
     moderator
    -0.06
     inve
    -0.06
     roam
    -0.06
    POSITIVE LOGITS
    SSH
    0.08
    icket
    0.07
    싱
    0.06
    ENSOR
    0.06
     Cri
    0.06
    ecake
    0.06
    Key
    0.06
     lis
    0.06
    exels
    0.06
    
    0.06
    Act Density 0.014%

    No Known Activations