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

    Neuronpedia

    INDEX
    Explanations

    measuring degree or type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     схема
    0.41
    遭到
    0.39
     Specifications
    0.39
     arma
    0.39
    هرات
    0.39
    телем
    0.38
     සිදු
    0.38
     никаких
    0.38
    carga
    0.37
    Additional
    0.37
    POSITIVE LOGITS
     faj
    0.38
    TestSource
    0.37
     ബി
    0.37
    }^{+}(
    0.36
    }}^{(
    0.36
    VerFile
    0.36
    hdfs
    0.36
    屎
    0.36
    ẩm
    0.34
    acetyl
    0.34
    Act Density 0.001%

    No Known Activations