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

    Neuronpedia

    INDEX
    Explanations

    receiving updates or status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ణ
    0.43
    ต่ำ
    0.43
     Expectations
    0.42
    น
    0.41
    状
    0.39
     thấp
    0.38
    盱
    0.38
     मोठी
    0.37
     मीडिया
    0.36
     профессор
    0.36
    POSITIVE LOGITS
    imread
    0.39
     !}{
    0.38
    orit
    0.37
     buddy
    0.37
    atschapp
    0.37
    agine
    0.36
     einges
    0.35
    periodic
    0.35
     obnov
    0.35
    登場
    0.34
    Act Density 0.000%

    No Known Activations