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

    Neuronpedia

    INDEX
    Explanations

    if number <=

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     underscored
    0.43
    शासित
    0.42
     underscore
    0.41
     столь
    0.40
    休み
    0.38
    剜
    0.37
     окра
    0.37
     Narrative
    0.36
     Stopped
    0.36
     বোঝা
    0.36
    POSITIVE LOGITS
     Međutim
    0.43
    oleh
    0.42
     ilmiah
    0.39
    .".
    0.38
    ového
    0.38
     sedangkan
    0.38
     Ubuy
    0.37
    "></
    0.36
     PSW
    0.36
     july
    0.36
    Act Density 0.000%

    No Known Activations