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

    Neuronpedia

    INDEX
    Explanations

    standard deviation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lonely
    -0.07
     courteous
    -0.06
    '/>
    -0.06
    _sim
    -0.06
    	con
    -0.06
    FRINGEMENT
    -0.06
     :.
    -0.06
     sollen
    -0.06
     wollte
    -0.06
     Royale
    -0.06
    POSITIVE LOGITS
     create
    0.06
    ductor
    0.06
    rength
    0.06
     Error
    0.06
    atars
    0.06
    HO
    0.06
    kaç
    0.06
    itical
    0.06
     SD
    0.06
     invent
    0.06
    Act Density 0.010%

    No Known Activations