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

    Neuronpedia

    INDEX
    Explanations

    grammar or rpg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ու
    0.51
    oten
    0.50
    otechnology
    0.49
    sam
    0.49
     மக்களின்
    0.49
    rium
    0.49
    相当于
    0.48
     सभी
    0.48
    ote
    0.48
     بال
    0.47
    POSITIVE LOGITS
    р
    0.52
     stran
    0.51
    Mockito
    0.50
     Hace
    0.50
    良い
    0.49
    ग्रस्त
    0.47
    Anche
    0.46
     dwa
    0.45
    Als
    0.44
    consin
    0.44
    Act Density 14.964%

    No Known Activations