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

    Neuronpedia

    INDEX
    Explanations

    ives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Disney
    -0.08
    �
    -0.07
     chocol
    -0.07
    attack
    -0.07
    Descriptors
    -0.07
     README
    -0.06
    ffff
    -0.06
    _ATOM
    -0.06
     Virtual
    -0.06
     regulatory
    -0.06
    POSITIVE LOGITS
    丁
    0.06
     즐
    0.06
     articles
    0.06
    	src
    0.06
     hil
    0.06
     archives
    0.06
    ін
    0.06
     iq
    0.06
    (O
    0.06
    ़े
    0.06
    Act Density 0.001%

    No Known Activations