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

    Neuronpedia

    INDEX
    Explanations

    ization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unknown
    -0.08
     :)
    -0.07
     ))↵↵
    -0.07
    狻
    -0.07
    常常
    -0.07
     המ
    -0.07
    芗
    -0.07
    救助
    -0.07
    𝙉
    -0.07
    备考
    -0.07
    POSITIVE LOGITS
    ieur
    0.07
     boil
    0.07
    揖
    0.07
    egrated
    0.07
     Model
    0.07
     jobId
    0.07
     النوع
    0.07
     jerk
    0.07
     وغير
    0.06
    /Edit
    0.06
    Act Density 0.004%

    No Known Activations