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

    Neuronpedia

    INDEX
    Explanations

    sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Client
    -0.07
     folding
    -0.06
    tea
    -0.06
     tercer
    -0.06
    .sound
    -0.06
     originates
    -0.06
     Kills
    -0.06
    .delta
    -0.06
    	Page
    -0.06
    ял
    -0.06
    POSITIVE LOGITS
    CAST
    0.07
    EXIT
    0.06
    COVER
    0.06
    erchant
    0.06
     expo
    0.06
    キング
    0.06
     **↵
    0.06
    .UseFont
    0.06
    zym
    0.05
     excluding
    0.05
    Act Density 0.030%

    No Known Activations