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

    Neuronpedia

    INDEX
    Explanations

    put up / on / in / to / it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ланти
    0.93
    Appro
    0.88
     Trapez
    0.87
    がら
    0.85
    gios
    0.82
    QUrl
    0.82
    𝗴
    0.82
     jede
    0.82
    Imagery
    0.81
     Bevölkerung
    0.81
    POSITIVE LOGITS
    atively
    1.48
     together
    1.21
     onus
    1.20
    Putting
    1.16
     aside
    1.16
     PUT
    1.12
     forth
    1.12
     put
    1.11
     Put
    1.11
     Putting
    1.09
    Act Density 0.040%

    No Known Activations