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

    Neuronpedia

    INDEX
    Explanations

    there is/might/was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.03
     의
    0.75
    ING
    0.70
    ो
    0.69
    ול
    0.69
     four
    0.68
     dabei
    0.68
     two
    0.67
     અહીં
    0.66
     minh
    0.66
    POSITIVE LOGITS
    ASF
    1.00
     serán
    0.95
     superflu
    0.95
     Lordships
    0.91
     iguales
    0.91
     serão
    0.89
    forc
    0.88
    asem
    0.88
    FORE
    0.87
    asat
    0.86
    Act Density 0.093%

    No Known Activations