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

    Neuronpedia

    INDEX
    Explanations

    global variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '}}
    -0.08
    Washington
    -0.07
    )}}
    -0.07
     Crash
    -0.07
     embassy
    -0.07
    seven
    -0.07
    }}
    -0.06
    ToolTip
    -0.06
    Fal
    -0.06
    ou
    -0.06
    POSITIVE LOGITS
     energetic
    0.07
    /DD
    0.06
     director
    0.06
    -browser
    0.06
     EventArgs
    0.06
    ोष
    0.06
    LEMENT
    0.06
    sizlik
    0.06
    yd
    0.06
    -byte
    0.06
    Act Density 0.006%

    No Known Activations