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

    Neuronpedia

    INDEX
    Explanations

    magnet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    coholic
    -0.07
             
↵
    -0.07
    �
    -0.07
     eax
    -0.06
    always
    -0.06
    private
    -0.06
     persists
    -0.06
     Yaz
    -0.06
    ):
↵
↵
    -0.06
     suggestive
    -0.06
    POSITIVE LOGITS
    abinet
    0.07
    icularly
    0.07
     inspect
    0.07
     Velocity
    0.06
    Ư�
    0.06
     Inter
    0.06
     vedle
    0.06
    ované
    0.06
    436
    0.06
     Entrepreneur
    0.06
    Act Density 0.001%

    No Known Activations