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

    Neuronpedia

    INDEX
    Explanations

    state of disappointment or issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     digo
    0.39
    élite
    0.38
     Qualifying
    0.37
    hangi
    0.37
    সে
    0.36
    软件包
    0.35
    édia
    0.35
    Кто
    0.35
    殚
    0.35
    Cert
    0.35
    POSITIVE LOGITS
     bilayer
    0.45
     пок
    0.43
     بیا
    0.43
    onan
    0.41
    <<"\
    0.40
     sajana
    0.40
    layers
    0.38
     sawdust
    0.38
     Hj
    0.38
    anen
    0.38
    Act Density 0.000%

    No Known Activations