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

    Neuronpedia

    INDEX
    Explanations

    divides or disassembly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     رحم
    0.49
     svou
    0.48
     从
    0.46
     dobře
    0.46
    十六章
    0.45
     proteine
    0.45
    困
    0.45
    文本
    0.44
     výkon
    0.44
    人之
    0.43
    POSITIVE LOGITS
    Fifth
    0.50
    Third
    0.50
     twists
    0.47
     barriers
    0.45
    Categories
    0.45
    eteers
    0.45
     losses
    0.44
    dif
    0.43
     processes
    0.43
    service
    0.43
    Act Density 0.002%

    No Known Activations