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

    Neuronpedia

    INDEX
    Explanations

    forehead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _appro
    -0.07
     assortment
    -0.07
     бути
    -0.07
    	items
    -0.07
    [data
    -0.07
     срав
    -0.07
     pnl
    -0.06
    vp
    -0.06
     hazards
    -0.06
     vessels
    -0.06
    POSITIVE LOGITS
     forehead
    0.08
    '
↵
↵
    0.07
    िद
    0.06
    Existing
    0.06
    (Operation
    0.06
    ']↵↵
    0.06
    arm
    0.06
    ↵↵
    0.06
            ↵    ↵
    0.06
    EXTERN
    0.06
    Act Density 0.007%

    No Known Activations