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

    Neuronpedia

    INDEX
    Explanations

    Galactic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    чні
    -0.07
     leopard
    -0.06
    round
    -0.06
    яс
    -0.06
    Neither
    -0.06
    ULE
    -0.06
    iceps
    -0.06
     llama
    -0.06
     mucho
    -0.06
    legs
    -0.06
    POSITIVE LOGITS
     Galactic
    0.08
    	CG
    0.07
    禁
    0.06
     logistic
    0.06
    하
    0.06
    grim
    0.06
     disrupted
    0.06
     швид
    0.06
     TRY
    0.06
    WH
    0.06
    Act Density 0.002%

    No Known Activations