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

    Neuronpedia

    INDEX
    Explanations

    future generations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    概
    -0.07
    挫
    -0.07
    uously
    -0.07
    ℏ
    -0.07
     Gro
    -0.07
     aims
    -0.07
     clauses
    -0.06
    なんか
    -0.06
     Cri
    -0.06
    启
    -0.06
    POSITIVE LOGITS
    istung
    0.09
     joystick
    0.08
    getId
    0.07
     --------↵
    0.07
     Convenient
    0.07
    HasColumnName
    0.07
     يعرف
    0.07
     аренд
    0.07
    egers
    0.07
    NamedQuery
    0.07
    Act Density 0.023%

    No Known Activations