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

    Neuronpedia

    INDEX
    Explanations

    Westfield

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     magic
    -0.06
     있으며
    -0.06
    	mov
    -0.06
     ترک
    -0.06
     cellar
    -0.06
    Slinky
    -0.06
     सद
    -0.06
    Biz
    -0.06
     CHANNEL
    -0.06
     shrugged
    -0.05
    POSITIVE LOGITS
    ,module
    0.07
    .Expression
    0.07
    εφ
    0.06
     skal
    0.06
    �
    0.06
    ,true
    0.06
    _indices
    0.06
     corrupted
    0.06
     muschi
    0.06
     neuen
    0.06
    Act Density 0.011%

    No Known Activations