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

    Neuronpedia

    INDEX
    Explanations

    reliance, money

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [to
    -0.08
     rol
    -0.07
     smiles
    -0.07
     tal
    -0.07
     Birth
    -0.07
     diamond
    -0.07
     있
    -0.07
    🎁
    -0.07
     TYPE
    -0.07
    (random
    -0.07
    POSITIVE LOGITS
    בטא
    0.07
    بات
    0.07
    ví
    0.07
    𨟠
    0.06
    pass
    0.06
    车队
    0.06
    Based
    0.06
    Rev
    0.06
     obsess
    0.06
    	root
    0.06
    Act Density 0.081%

    No Known Activations