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

    Neuronpedia

    INDEX
    Explanations

    explicitly or implied

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    묭
    0.44
     وخت
    0.43
    ᕝ
    0.42
     piè
    0.40
    StarCore
    0.40
     voet
    0.39
     baos
    0.38
    velle
    0.38
     सेटअप
    0.38
    gitian
    0.38
    POSITIVE LOGITS
     externally
    0.43
     expressed
    0.40
     LEGAL
    0.40
     Extern
    0.40
    Extern
    0.38
     symbolically
    0.38
     extern
    0.38
     forecasted
    0.38
     Expressway
    0.38
    Park
    0.38
    Act Density 0.001%

    No Known Activations