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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Saved
    -0.07
    ENTS
    -0.07
     üzerindeki
    -0.06
     bes
    -0.06
    aims
    -0.06
     pago
    -0.06
    警
    -0.06
    't
    -0.06
     club
    -0.06
    ΗΜ
    -0.06
    POSITIVE LOGITS
    usra
    0.08
     واحد
    0.07
    .rdf
    0.07
    ınıf
    0.07
    ourney
    0.07
    ufreq
    0.06
    essenger
    0.06
     userProfile
    0.06
     Mant
    0.06
    _consum
    0.06
    Act Density 0.015%

    No Known Activations