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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ei
    -0.06
     공식
    -0.06
    _inv
    -0.06
     Navbar
    -0.06
     Multi
    -0.06
     scripts
    -0.05
    al
    -0.05
     oppressive
    -0.05
    	username
    -0.05
     enumeration
    -0.05
    POSITIVE LOGITS
     �
    0.07
    崇
    0.07
    IMAL
    0.07
    отв
    0.07
    ाव
    0.07
    (bbox
    0.06
    �述
    0.06
    同時
    0.06
    вод
    0.06
    ecessarily
    0.06
    Act Density 0.275%

    No Known Activations