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

    Neuronpedia

    INDEX
    Explanations

    Okay, I can help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     activities
    0.49
    activities
    0.40
     aktivnosti
    0.39
     service
    0.39
     engulf
    0.39
     finance
    0.38
     characteristic
    0.38
     Aktivitäten
    0.38
     bank
    0.37
     Zo
    0.37
    POSITIVE LOGITS
    番
    0.42
     escrito
    0.37
     lapin
    0.37
    反而
    0.36
    GEST
    0.36
    ┄
    0.36
    ču
    0.35
     viên
    0.34
     करार
    0.34
    ResponseWriter
    0.34
    Act Density 0.000%

    No Known Activations