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

    Neuronpedia

    INDEX
    Explanations

    design

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="../../../
    -0.07
    stan
    -0.06
     hips
    -0.06
    lm
    -0.06
    бра
    -0.06
    asan
    -0.06
    used
    -0.06
     mó
    -0.06
    -Y
    -0.06
     структу
    -0.06
    POSITIVE LOGITS
    ッシュ
    0.08
    оратив
    0.07
     Justice
    0.06
     aspiring
    0.06
     Early
    0.06
     �
    0.06
    NEXT
    0.06
    ichi
    0.06
    文学
    0.06
    แรง
    0.06
    Act Density 0.024%

    No Known Activations