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

    Neuronpedia

    INDEX
    Explanations

    making decisions, setting limits, or uploading files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дни
    0.41
     skrz
    0.41
     almacenar
    0.39
     masker
    0.39
    лох
    0.38
     läbi
    0.38
    ईन
    0.38
    ద్
    0.38
     recibir
    0.38
    समय
    0.38
    POSITIVE LOGITS
     institutions
    0.42
     প্রতিক
    0.39
     rising
    0.38
     terrestrial
    0.37
     permission
    0.37
     MIM
    0.37
     engine
    0.37
     remediation
    0.37
     runtime
    0.37
     competency
    0.36
    Act Density 0.000%

    No Known Activations