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

    Neuronpedia

    INDEX
    Explanations

    Database connections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    랏
    -0.08
    رش
    -0.07
    ชนะ
    -0.07
    𝕏
    -0.07
     planted
    -0.07
    درج
    -0.07
    蓍
    -0.07
    陷阱
    -0.06
    繇
    -0.06
    POSITIVE LOGITS
    #ifdef
    0.08
    zech
    0.08
     uri
    0.07
     NUMBER
    0.07
    authors
    0.07
    -kind
    0.07
     reporting
    0.07
    ío
    0.07
    Fre
    0.07
    _len
    0.06
    Act Density 0.006%

    No Known Activations