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

    Neuronpedia

    INDEX
    Explanations

    replaced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    üm
    -0.06
     positivity
    -0.06
     MF
    -0.06
    meleri
    -0.06
    .D
    -0.06
    aticon
    -0.06
    MF
    -0.06
     αρχ
    -0.06
    Wa
    -0.06
    CTION
    -0.06
    POSITIVE LOGITS
    953
    0.07
     chickens
    0.07
    いや
    0.07
    _##
    0.06
     Reaper
    0.06
     cereal
    0.06
     ANY
    0.06
    ,y
    0.06
    	field
    0.06
     Holidays
    0.06
    Act Density 0.001%

    No Known Activations