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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    שמר
    -0.07
    ি�
    -0.07
     withd
    -0.07
    пси
    -0.07
     labels
    -0.06
     undergrad
    -0.06
     safeg
    -0.06
    sg
    -0.06
    盈
    -0.06
    watch
    -0.06
    POSITIVE LOGITS
    _ORDER
    0.08
    🚪
    0.08
    'order
    0.07
     în
    0.07
    phant
    0.07
     DRIVE
    0.07
     eller
    0.07
    亨
    0.07
    ◻
    0.07
    ]string
    0.07
    Act Density 0.003%

    No Known Activations