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

    Neuronpedia

    INDEX
    Explanations

    weighing factors and considerations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reg
    -0.07
     adjustment
    -0.07
    ่อม
    -0.07
    .End
    -0.07
    Coll
    -0.06
     united
    -0.06
     expl
    -0.06
     slides
    -0.06
    763
    -0.06
     increase
    -0.06
    POSITIVE LOGITS
    FORMATION
    0.07
     Electoral
    0.06
    parable
    0.06
    ])->
    0.06
    ('/')[-
    0.06
    ��
    0.06
     porad
    0.06
    ีน
    0.06
     Antar
    0.06
    WillDisappear
    0.06
    Act Density 0.240%

    No Known Activations