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

    Neuronpedia

    INDEX
    Explanations

    general advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Transcript
    -0.08
    丢失
    -0.07
    cript
    -0.07
     Terrace
    -0.07
     소
    -0.07
    -effects
    -0.07
    당
    -0.07
    -tax
    -0.07
    .Screen
    -0.07
    نفذ
    -0.07
    POSITIVE LOGITS
    ᱚ
    0.07
     origins
    0.06
    /image
    0.06
    .GroupLayout
    0.06
     ihtiya
    0.06
     clim
    0.06
     transitional
    0.06
    𐰇
    0.06
    ��
    0.06
    뤽
    0.06
    Act Density 0.038%

    No Known Activations