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

    Neuronpedia

    INDEX
    Explanations

    Jan

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frog
    -0.07
    _bag
    -0.06
     ModelRenderer
    -0.06
     additives
    -0.06
     полностью
    -0.06
     Başkanı
    -0.06
    (search
    -0.06
     buses
    -0.06
     selber
    -0.06
    _legend
    -0.06
    POSITIVE LOGITS
     je
    0.07
    여
    0.07
    answered
    0.07
    ิงหาคม
    0.06
    inished
    0.06
    達
    0.06
    ाफ
    0.06
    �
    0.06
     kotlinx
    0.06
    缓
    0.06
    Act Density 0.002%

    No Known Activations