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

    Neuronpedia

    INDEX
    Explanations

    ative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rhodes
    -0.07
     malaria
    -0.07
    σο
    -0.06
     scattering
    -0.06
     disadv
    -0.06
     분야
    -0.06
     ва
    -0.06
     unusual
    -0.06
     dies
    -0.06
     إل
    -0.06
    POSITIVE LOGITS
    ByID
    0.07
     budou
    0.06
     cre
    0.06
     李
    0.06
    .Include
    0.06
    DBC
    0.06
    .amazonaws
    0.06
    -contrib
    0.06
    unan
    0.06
    名
    0.06
    Act Density 0.005%

    No Known Activations