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
     sinh
    -0.06
     دختر
    -0.06
    Vs
    -0.06
    되는
    -0.06
     خانه
    -0.06
    최
    -0.06
     변화
    -0.06
     Chloe
    -0.06
    ح
    -0.06
     також
    -0.06
    POSITIVE LOGITS
     specialists
    0.07
     protector
    0.06
     temsil
    0.06
     barrage
    0.06
    äge
    0.06
    (version
    0.06
    amation
    0.06
     engaged
    0.06
     commitments
    0.06
     LTE
    0.06
    Act Density 0.014%

    No Known Activations