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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    早
    -0.07
     indifference
    -0.07
    aits
    -0.07
     kW
    -0.07
     trapping
    -0.06
     Zub
    -0.06
     epochs
    -0.06
    ฮ
    -0.06
     dados
    -0.06
     Dez
    -0.06
    POSITIVE LOGITS
    _NEG
    0.06
    فی
    0.06
    _pe
    0.06
     emerged
    0.06
     quil
    0.06
    .n
    0.06
    ippers
    0.06
     parç
    0.06
    IFICATE
    0.05
     emerges
    0.05
    Act Density 0.022%

    No Known Activations