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

    Neuronpedia

    INDEX
    Explanations

    stamp collecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    1.34
    는
    1.27
    ۔
    1.16
    मा
    1.00
    2
    0.96
    )
    0.93
    ਰ
    0.92
     cuddling
    0.92
    ;*/
    0.91
    та
    0.89
    POSITIVE LOGITS
     Stamp
    1.25
    Stamp
    1.23
    have
    1.02
     Stamps
    1.02
     stamps
    1.01
     Have
    0.92
    stamp
    0.92
    be
    0.92
    Have
    0.88
     stamp
    0.88
    Act Density 0.001%

    No Known Activations